© 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-16K
    7. 10121
    Prev
    Next
    INDEX
    Explanations

    sea and marine nouns

    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
    s
    1.02
     ইমাম
    0.95
    ені
    0.94
    mia
    0.87
    க
    0.85
    侾
    0.85
    st
    0.85
    onError
    0.82
    র
    0.81
     OSA
    0.81
    POSITIVE LOGITS
    foam
    1.07
    嘯
    0.97
     cual
    0.93
    峽
    0.92
     Pines
    0.88
     urch
    0.88
     Âu
    0.88
    िख
    0.87
     לצ
    0.85
     breezes
    0.85
    Activations Density 0.040%

    No Known Activations