© 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. 87546
    Prev
    Next
    INDEX
    Explanations

    acceptedassumptions

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

    prediction scores and code

    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
    @
    0.40
     Arora
    0.40
     Digital
    0.39
     Techn
    0.38
     Desktop
    0.37
    &
    0.37
     Ağustos
    0.37
     Tecn
    0.36
     oraz
    0.36
    фа
    0.35
    POSITIVE LOGITS
    鐲
    0.40
    ahankan
    0.38
    acuation
    0.38
    stepToken
    0.37
    髻
    0.37
    秧
    0.37
    䳕
    0.36
     صي
    0.35
     embol
    0.35
    舫
    0.35
    Activations Density 0.002%

    No Known Activations