Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7835
    Prev
    Next
    INDEX
    Explanations

    focus on writing

    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_9_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
    πει
    1.23
     worst
    1.14
    worst
    1.10
    Worst
    1.10
    entimes
    1.08
    ে
    1.05
    ⃝
    1.04
    SIGN
    1.00
     clarification
    1.00
    󠁿
    0.98
    POSITIVE LOGITS
    jenigen
    1.47
    uzione
    1.38
    cus
    1.36
     목적
    1.33
    cion
    1.32
     nabí
    1.30
    已知
    1.28
    ll
    1.27
    য়ার
    1.26
    ctor
    1.25
    Activations Density 0.000%

    No Known Activations