© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8077
    Prev
    Next
    INDEX
    Explanations

    salutations and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    "> 
    -2.69
    oluene
    -2.66
    
    -2.52
    踟
    -2.45
    ieR
    -2.44
    平常
    -2.41
    睺
    -2.41
     notorious
    -2.41
    媾
    -2.41
    迨
    -2.31
    POSITIVE LOGITS
    蛧
    3.72
    in
    3.23
    नलोड
    2.64
    begin
    2.39
    </h5>
    2.38
    t
    2.25
     这
    2.22
    section
    2.22
    ");
    2.16
    </b>
    2.14
    Activations Density 0.175%

    No Known Activations