© 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. 7580
    Prev
    Next
    INDEX
    Explanations

    experiencing enjoyment

    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
    و
    1.13
     расстоя
    1.07
    тың
    1.06
    $>
    1.04
    ia
    1.04
     стане
    0.97
    en
    0.95
     eind
    0.95
     već
    0.94
     între
    0.93
    POSITIVE LOGITS
     speculating
    1.33
     immensely
    1.32
    л
    1.23
    t
    1.22
     exploring
    1.18
     watching
    1.17
     revisiting
    1.16
    ably
    1.16
     experimenting
    1.12
    talking
    1.10
    Activations Density 0.013%

    No Known Activations