© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112560
    Prev
    Next
    INDEX
    Explanations

    free download, stop when

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

    dominant roleplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siblings
    0.52
     shares
    0.47
     parties
    0.44
     tricky
    0.44
    是因為
    0.43
     headroom
    0.42
     shared
    0.42
     o
    0.41
     mop
    0.41
     troubled
    0.40
    POSITIVE LOGITS
     Ländern
    0.47
     Nationen
    0.47
    det
    0.46
    本土
    0.46
    д
    0.46
    Countries
    0.46
    Countdown
    0.46
    各国
    0.45
     ת
    0.44
     మీద
    0.44
    Activations Density 0.000%

    No Known Activations