© 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. 71001
    Prev
    Next
    INDEX
    Explanations

    secret deals, message ordering, driving with

    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
    ak
    0.53
    З
    0.52
    )}`;
    0.46
    `<
    0.46
    КА
    0.46
     الز
    0.45
    ᆯ
    0.45
    ಮ್
    0.45
    ccbp
    0.44
    य
    0.44
    POSITIVE LOGITS
    Heart
    0.44
    Hearts
    0.42
     obie
    0.41
     Foxes
    0.40
    archiwizowane
    0.40
     beeh
    0.40
    Face
    0.40
     printemps
    0.40
     Somerville
    0.40
    Alo
    0.40
    Activations Density 0.004%

    No Known Activations