© 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-16K
    7. 13631
    Prev
    Next
    INDEX
    Explanations

    salutations and specifics

    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_16k_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
    .)
    0.49
     its
    0.41
    ె
    0.39
    發生
    0.39
     teen
    0.38
    れます
    0.38
    緊
    0.38
    ष्ट
    0.38
    తర
    0.38
    <0x9D>
    0.38
    POSITIVE LOGITS
     facile
    0.48
     waypoint
    0.46
     mechanistic
    0.44
    Sequential
    0.44
     capacitor
    0.44
     backtrack
    0.43
     quaternary
    0.43
     sortBy
    0.43
     சந்தி
    0.42
     serpent
    0.42
    Activations Density 0.041%

    No Known Activations