© 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. 31-GEMMASCOPE-2-RES-262K
    7. 51006
    Prev
    Next
    INDEX
    Explanations

    given initial state

    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_31_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
     landscaped
    0.32
     cellulose
    0.31
     greens
    0.27
     flavonoids
    0.27
    AxisAlignment
    0.27
     hammock
    0.27
    ;%(
    0.27
     ডেস্ক
    0.26
     grom
    0.26
    ］
    0.26
    POSITIVE LOGITS
     Daunting
    0.38
     ipsa
    0.38
     vehement
    0.36
     เอก
    0.36
     Մ
    0.36
    殚
    0.35
     właścic
    0.35
    ✠
    0.35
    ا
    0.34
     vollständ
    0.34
    Activations Density 0.002%

    No Known Activations