© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    begin, dispense, dissect, start, get

    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
    twilio
    1.19
    ন্তী
    1.18
    𒁀
    1.18
    是對
    1.18
    Ϥ
    1.18
    <unused973>
    1.15
    BeforeText
    1.15
    ynb
    1.14
    ামুটি
    1.14
    FRINGEMENT
    1.14
    POSITIVE LOGITS
    ル
    0.94
     Avrupa
    0.93
    teen
    0.89
    ই
    0.89
    ി
    0.86
     answered
    0.86
     öğren
    0.83
     gis
    0.83
    c
    0.82
     Öğ
    0.81
    Activations Density 0.001%

    No Known Activations