© 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. 7010
    Prev
    Next
    INDEX
    Explanations

    php app namespace

    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
    :**
    0.77
    เอา
    0.75
    '_
    0.70
    ccionar
    0.69
    .**
    0.69
     เอา
    0.67
    **:
    0.67
    ™
    0.67
    Vad
    0.67
    止
    0.67
    POSITIVE LOGITS
     locality
    0.95
     localities
    0.92
    hdd
    0.90
    öger
    0.90
    үм
    0.89
    œurs
    0.89
    örungen
    0.89
     toilets
    0.88
     devastation
    0.87
    řeb
    0.87
    Activations Density 0.001%

    No Known Activations