© 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-65K
    7. 1322
    Prev
    Next
    INDEX
    Explanations

    common phrases

    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_65k_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
     phospholipid
    0.45
     transient
    0.40
    Blocked
    0.40
     transients
    0.40
     notifications
    0.39
     OEM
    0.39
     buildings
    0.38
    َّة
    0.38
     targets
    0.37
     athletes
    0.37
    POSITIVE LOGITS
     மர
    0.56
     αγο
    0.55
    leş
    0.54
     வர
    0.52
    ם
    0.52
    Tabla
    0.52
    vote
    0.51
     bordo
    0.51
    𝒏
    0.51
    Tes
    0.51
    Activations Density 0.000%

    No Known Activations