© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7710
    Prev
    Next
    INDEX
    Explanations

    how different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    statistik
    0.55
    któ
    0.52
    dni
    0.51
     communauté
    0.49
    <unused23>
    0.49
    จุบัน
    0.48
    Scient
    0.47
    órc
    0.47
    旕
    0.47
    تهي
    0.47
    POSITIVE LOGITS
     dozens
    0.51
     eddies
    0.51
     thousands
    0.49
     DOOR
    0.47
     scammers
    0.47
     hundreds
    0.46
     YELLOW
    0.46
     Abra
    0.46
     HYDRO
    0.45
     Deposits
    0.45
    Activations Density 0.001%

    No Known Activations