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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119405
    Prev
    Next
    INDEX
    Explanations

    conditions and forms

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

    The neuron fires on common open‐source license boilerplate phrases—especially terms about “source and binary forms,” redistribution conditions, disclaimers (“AS IS,” “without warranties”), and related license notices.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ();
    -1.08
    Aktualisiert
    -1.05
     titoli
    -0.96
    }$
    -0.94
     amid
    -0.94
    SI
    -0.94
     of
    -0.94
    ]]
    -0.93
    ;
    -0.93
    }$.
    -0.92
    POSITIVE LOGITS
    ,
    2.03
    ،
    1.16
     gouvern
    1.07
    لباس
    1.05
     empêcher
    1.03
    ​,
    1.02
     célè
    1.01
    Magdalena
    1.00
     tomber
    1.00
    ²,
    0.99
    Activations Density 0.560%

    No Known Activations