© 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. 53-GEMMASCOPE-2-RES-262K
    7. 83269
    Prev
    Next
    INDEX
    Explanations

    basalt, lava, volcanic rock

    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_53_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
    变形
    0.40
    活跃
    0.38
    誊
    0.38
    یداری
    0.37
     الترم
    0.37
     শৃ
    0.37
    வரை
    0.36
    窕
    0.36
    压力
    0.35
     prayed
    0.35
    POSITIVE LOGITS
     basalt
    1.11
     lava
    0.93
    bas
    0.79
     basal
    0.78
     Bas
    0.77
     maf
    0.76
     база
    0.76
     oliv
    0.75
    Bas
    0.73
     basaltes
    0.73
    Activations Density 0.013%

    No Known Activations