© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10072
    Prev
    Next
    INDEX
    Explanations

    inner self and past struggles

    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_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
    感
    0.72
     sacraments
    0.69
     নিঃ
    0.69
    కుల
    0.67
     feeling
    0.66
    eluk
    0.66
     وصحبه
    0.65
    haar
    0.65
     感
    0.65
     occupancy
    0.65
    POSITIVE LOGITS
     inner
    1.67
    inner
    1.45
     Inner
    1.43
     inside
    1.38
    Inner
    1.36
     внутренних
    1.34
    inside
    1.29
     внутріш
    1.29
     internal
    1.28
     dormant
    1.28
    Activations Density 0.122%

    No Known Activations