© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 110766
    Prev
    Next
    INDEX
    Explanations

    list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    えると
    0.38
     montre
    0.38
    𝓌
    0.38
    𝓀
    0.38
     aparece
    0.37
     alternating
    0.37
    )++;
    0.36
    ᆷ
    0.36
    verifica
    0.36
     numb
    0.36
    POSITIVE LOGITS
     لص
    0.50
     Clubhouse
    0.42
    PORTS
    0.40
     gelegt
    0.39
     Naked
    0.39
     ダンロップ
    0.38
    Ships
    0.38
    hank
    0.38
    燚
    0.37
     pianos
    0.37
    Activations Density 0.000%

    No Known Activations