© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13378
    Prev
    Next
    INDEX
    Explanations

    topics, questions, and concepts

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

    The neuron fires on content-bearing words (key nouns and verbs) rather than on high-frequency function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。
    1.34
    ."
    1.28
    }$.
    1.27
    ។
    1.27
    $.
    1.27
    ".
    1.26
    .”
    1.22
    ”.
    1.22
    }.
    1.20
    '.
    1.17
    POSITIVE LOGITS
    ?),
    1.91
    ...),
    1.88
    ?”,
    1.65
    ),
    1.59
     ...,
    1.59
    ?',
    1.59
     [],
    1.58
     ),
    1.56
     ],
    1.54
     "",
    1.54
    Activations Density 0.072%

    No Known Activations