© 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. 84160
    Prev
    Next
    INDEX
    Explanations

    spotting, waves, breeze

    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
     ethics
    0.39
     Willey
    0.39
    idavit
    0.39
     readiness
    0.38
    ॲ
    0.38
     adjuvant
    0.37
     catalysts
    0.36
     Kyi
    0.36
     algebras
    0.36
     jasper
    0.35
    POSITIVE LOGITS
    Ы
    0.42
    onz
    0.40
    కోండి
    0.39
    auschen
    0.39
    れます
    0.38
     தொலை
    0.38
     зда
    0.37
    sects
    0.37
    ommen
    0.37
    ärts
    0.37
    Activations Density 0.000%

    No Known Activations