© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14300
    Prev
    Next
    INDEX
    Explanations

    range of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    session
    0.82
     session
    0.77
    Session
    0.75
    last
    0.74
    ession
    0.74
    pub
    0.67
    ()-
    0.67
    regulated
    0.64
     தொடங்கிய
    0.64
    SESSION
    0.63
    POSITIVE LOGITS
    燵
    0.76
     Communic
    0.74
    ട്ടില്‍
    0.73
     TInner
    0.70
    Communic
    0.69
     Happen
    0.68
     Communication
    0.68
     Maxim
    0.67
    ாலை
    0.66
     maître
    0.66
    Activations Density 0.042%

    No Known Activations