© 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. 49311
    Prev
    Next
    INDEX
    Explanations

    their effort

    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
    acious
    0.49
    ,
    0.47
    这个
    0.46
     *,
    0.46
     ſh
    0.46
     \
    0.46
    ，
    0.44
    N
    0.44
     、,
    0.43
    _,
    0.42
    POSITIVE LOGITS
     связь
    0.50
    ಕ್ಕಿಂತ
    0.50
     التواصل
    0.48
    ဝန်
    0.46
    Civita
    0.45
     kavram
    0.45
    ناسب
    0.43
    りに
    0.42
    Connection
    0.42
     pemasaran
    0.42
    Activations Density 0.013%

    No Known Activations