© 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. 49256
    Prev
    Next
    INDEX
    Explanations

    than

    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
     уроке
    0.48
     여러
    0.47
     stargazerCount
    0.46
     进行
    0.45
    消毒
    0.43
    🈶
    0.43
     실수
    0.42
    댓글
    0.42
    𒈠
    0.42
     রকম
    0.42
    POSITIVE LOGITS
    MM
    0.42
     B
    0.39
    _
    0.39
     I
    0.39
    ERS
    0.38
    NC
    0.38
    ಂಕ್
    0.38
    AL
    0.38
    переди
    0.37
     Cone
    0.36
    Activations Density 0.005%

    No Known Activations