© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110710
    Prev
    Next
    INDEX
    Explanations

    ****** separators and placeholders

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

    LaTeX backslash commands or code-related syntax patterns (particularly backslashes followed by mathematical or programming notation).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h2>
    -2.98
    ?
    -2.89
    ).
    -2.81
     "
    -2.61
    瞅
    -2.41
    '.
    -2.33
    {
    -2.25
    豈
    -2.23
     :/
    -2.22
     neues
    -2.22
    POSITIVE LOGITS
    }}\
    2.94
    她
    2.91
     mereka
    2.56
    Ꮸ
    2.22
    gucig
    2.17
    ：@
    2.17
     môžu
    2.14
    垆
    2.09
    他们
    2.08
    　　(
    2.06
    Activations Density 0.001%

    No Known Activations