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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111180
    Prev
    Next
    INDEX
    Explanations

    Okay, conversational continuations

    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
    ография
    0.48
    ませんか
    0.44
     Bihar
    0.44
    ংস
    0.43
    ですし
    0.43
     Sd
    0.42
    您的
    0.42
    ]=-
    0.42
    Bihar
    0.42
     alebo
    0.41
    POSITIVE LOGITS
    are
    0.63
    state
    0.54
    es
    0.53
    iss
    0.53
     sleek
    0.52
    ri
    0.52
    area
    0.51
    off
    0.49
    air
    0.49
    rice
    0.48
    Activations Density 0.003%

    No Known Activations