© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92659
    Prev
    Next
    INDEX
    Explanations

    reversal, apologizing, brainstorming, imagine, stopping

    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
     கெல்வின்
    0.56
    jourd
    0.54
    Ꮽ
    0.54
    νης
    0.53
    hounds
    0.52
     στη
    0.51
    Dame
    0.50
    GoAbroad
    0.50
    Stabilise
    0.50
    ଡ
    0.50
    POSITIVE LOGITS
     more
    0.49
    ↵↵
    0.48
     (
    0.47
    ↵
    0.47
     $
    0.44
     It
    0.44
     Ts
    0.40
     castles
    0.40
     mysterious
    0.40
    CH
    0.40
    Activations Density 0.014%

    No Known Activations