© 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. 10-GEMMASCOPE-RES-131K
    4. 68862
    Prev
    Next
    INDEX
    Explanations

    reports followed by a colon

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

    The neuron detects tokens that introduce or point to external references or navigation cues—bylines, hyperlinks, or “read more”-type pointers (e.g. “via,” “reports,” colons, “below,” “more info,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     then
    -1.59
     but
    -1.43
     somewhat
    -1.41
     not
    -1.39
    if
    -1.38
     большин
    -1.38
     платье
    -1.29
     duk
    -1.26
     later
    -1.25
     no
    -1.24
    POSITIVE LOGITS
    .
    1.55
     with
    1.55
     from
    1.49
     on
    1.36
    </strong>
    1.32
     tilgjenge
    1.20
    gjenge
    1.20
    ம
    1.16
     alebo
    1.14
    الغ
    1.13
    Activations Density 0.028%

    No Known Activations