© 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-262K
    7. 5796
    Prev
    Next
    INDEX
    Explanations

    Ingredients followed by colon

    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_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
    apanicola
    0.33
    큽
    0.31
     matchs
    0.31
    лять
    0.30
    ట్లా
    0.30
     énorm
    0.30
     endomet
    0.30
     उर्फी
    0.30
    酈
    0.30
    ：
    0.30
    POSITIVE LOGITS
     Ar
    0.34
     I
    0.33
     Continuing
    0.31
     Int
    0.30
     North
    0.30
    ic
    0.29
     myself
    0.29
     they
    0.29
    ini
    0.29
    ri
    0.29
    Activations Density 0.012%

    No Known Activations