© 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. 30657
    Prev
    Next
    INDEX
    Explanations

    questions for clarification

    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
    ᐈ
    0.46
    ٤
    0.42
    ktops
    0.41
    abt
    0.41
    ft
    0.41
    ƣ
    0.40
    4
    0.40
    ٨
    0.38
    ampe
    0.38
    ৪৮
    0.38
    POSITIVE LOGITS
     Chromatography
    0.47
     Christophe
    0.38
     Elderly
    0.38
     Claudio
    0.38
     Clio
    0.37
     જિલ્
    0.37
     Fam
    0.37
     briefings
    0.37
     pabbaj
    0.36
     Hannah
    0.36
    Activations Density 0.000%

    No Known Activations