© 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. 17-GEMMASCOPE-2-RES-16K
    7. 16338
    Prev
    Next
    INDEX
    Explanations

    weekly or monthly plans

    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_17_width_16k_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
    م
    3.97
    ו
    3.25
    로
    2.66
     doba
    2.65
    ه
    2.61
    м
    2.50
    й
    2.50
     staw
    2.50
    asd
    2.48
    に
    2.41
    POSITIVE LOGITS
     unarmed
    2.74
    ことになる
    2.52
     lymphoma
    2.36
    gomery
    2.30
     tease
    2.26
    Одна
    2.25
    വ്ര
    2.24
    ends
    2.18
    сим
    2.16
    ſelf
    2.14
    Activations Density 0.037%

    No Known Activations