© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10124
    Prev
    Next
    INDEX
    Explanations

    from scratch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MORPH
    0.86
    advanced
    0.84
     Осо
    0.82
    essayer
    0.80
    噤
    0.78
    覓
    0.78
    ందించ
    0.76
     বুল
    0.75
     一般
    0.75
     పెట్టు
    0.75
    POSITIVE LOGITS
     jon
    1.03
     solos
    0.97
     solo
    0.95
     Ding
    0.93
     Solo
    0.92
    충
    0.91
    듬
    0.88
     Carg
    0.86
     Cargo
    0.86
     SOLO
    0.85
    Activations Density 0.055%

    No Known Activations