© 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. 34-GEMMASCOPE-RES-131K
    7. 93095
    Prev
    Next
    INDEX
    Explanations

    Vikram, Vicki, Vick names

    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_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
    ضم
    -0.73
    toastr
    -0.73
     kolorze
    -0.71
    currentValue
    -0.69
     existente
    -0.68
     Netz
    -0.66
    TextEditing
    -0.65
    volte
    -0.63
    ัต
    -0.63
     пы
    -0.63
    POSITIVE LOGITS
    gulan
    0.84
     Designated
    0.74
     glacial
    0.74
    Vect
    0.74
    forza
    0.74
     syndromes
    0.73
     conveyance
    0.72
    ignez
    0.72
     Vik
    0.72
    chwitz
    0.71
    Activations Density 0.010%

    No Known Activations