© 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. 47193
    Prev
    Next
    INDEX
    Explanations

    no, absence, limited

    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
     neph
    0.40
    oglio
    0.40
    ?...
    0.40
    ataya
    0.39
    ಶಸ್
    0.39
     অবশ্য
    0.38
    >("
    0.38
    »).
    0.38
    👳
    0.38
     handcuffed
    0.38
    POSITIVE LOGITS
    s
    0.46
     absence
    0.45
    ll
    0.42
    a
    0.42
     K
    0.41
     هناك
    0.41
     aparent
    0.40
     conforme
    0.40
     Absence
    0.40
     Beau
    0.40
    Activations Density 0.001%

    No Known Activations