© 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. 15816
    Prev
    Next
    INDEX
    Explanations

    system calls

    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
    
    0.41
    bcc
    0.39
    ни
    0.37
    за
    0.36
     δια
    0.36
     سؤال
    0.35
     immediatamente
    0.35
     dramatically
    0.35
     انٹر
    0.35
     ɛ
    0.35
    POSITIVE LOGITS
     clashes
    0.42
    ᚋ
    0.40
     तबीयत
    0.39
     clashed
    0.38
    츨
    0.38
    所谓
    0.38
    toprule
    0.38
    ambahkan
    0.37
    잦
    0.36
     clash
    0.36
    Activations Density 0.015%

    No Known Activations