© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33651
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by words that introduce or participate in “to-infinitive” constructions (e.g. eager to, a lot to be, mostly bought, begin to feel).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ();}
    -1.32
    是一个
    -1.30
     is
    -1.30
    是个
    -1.23
     was
    -1.23
     });
    
    -1.22
    };
    -1.20
    ()};
    -1.20
     since
    -1.19
    ()));
    
    -1.18
    POSITIVE LOGITS
     themselves
    3.22
     their
    2.95
    themselves
    2.50
     jejich
    2.14
     Their
    1.96
    Their
    1.91
    their
    1.82
     их
    1.79
     leurs
    1.68
     they
    1.61
    Activations Density 0.043%

    No Known Activations