© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3871
    Prev
    Next
    INDEX
    Explanations

    time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     vết
    0.55
    ự
    0.53
     realizando
    0.52
     požad
    0.52
    昰
    0.52
     gesam
    0.51
     którzy
    0.50
     valamint
    0.50
     Zeiten
    0.50
    ০০
    0.49
    POSITIVE LOGITS
    its
    0.65
    5
    0.56
    momentum
    0.56
    mation
    0.55
    mers
    0.53
    speople
    0.53
    4
    0.53
    out
    0.52
    mix
    0.52
    ers
    0.51
    Activations Density 0.301%

    No Known Activations