© 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. 13077
    Prev
    Next
    INDEX
    Explanations

    structured text separators

    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
    in
    0.35
    two
    0.35
     The
    0.35
     I
    0.35
    if
    0.34
    ı
    0.34
    other
    0.34
    alt
    0.34
    all
    0.34
     G
    0.34
    POSITIVE LOGITS
     isotherm
    0.38
     agglomer
    0.38
     emuls
    0.37
    Pyrimidine
    0.36
     symbi
    0.36
     biofilms
    0.36
     terpenes
    0.35
     uridine
    0.34
     توان
    0.34
     acry
    0.34
    Activations Density 0.183%

    No Known Activations