© 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. 78812
    Prev
    Next
    INDEX
    Explanations

    code, test, documentation

    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
    Investor
    -0.76
     Investor
    -0.75
     investor
    -0.71
    aufen
    -0.68
     Epp
    -0.66
    Tarih
    -0.65
     Audubon
    -0.65
    Ἑ
    -0.64
     wyda
    -0.64
     دوس
    -0.62
    POSITIVE LOGITS
    妣
    0.73
    ♱
    0.71
     Salah
    0.70
     Stich
    0.68
     Cia
    0.65
    ตะ
    0.64
    blatt
    0.64
    stam
    0.62
     Ralf
    0.62
    SubType
    0.62
    Activations Density 0.047%

    No Known Activations