© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63795
    Prev
    Next
    INDEX
    Explanations

    framework test license

    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
    stm
    -0.76
    Insider
    -0.71
    insider
    -0.69
     corect
    -0.69
     Listener
    -0.69
     PROM
    -0.67
     質
    -0.67
     Durchsch
    -0.66
    PREF
    -0.66
    Unity
    -0.65
    POSITIVE LOGITS
     pił
    0.71
     trim
    0.67
     however
    0.66
    宴会
    0.65
     plates
    0.65
     fortune
    0.63
     curry
    0.63
     face
    0.63
    ensacola
    0.63
    DECLARE
    0.62
    Activations Density 0.049%

    No Known Activations