© 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. 110952
    Prev
    Next
    INDEX
    Explanations

    perfectly linear calculations

    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
     compuls
    0.44
    ESSIONS
    0.44
     fortune
    0.39
     compulsion
    0.39
     شە
    0.39
     peran
    0.39
    㫙
    0.38
    哽
    0.37
     आक्रमण
    0.37
     popOperand
    0.37
    POSITIVE LOGITS
    zoa
    0.42
    Chat
    0.39
    awatir
    0.39
    Torrent
    0.38
    osa
    0.37
    hose
    0.37
    azed
    0.37
    Want
    0.37
     इसे
    0.36
    allic
    0.36
    Activations Density 0.000%

    No Known Activations