© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    quantities and ranges

    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
     formData
    0.29
    <unused1112>
    0.29
    စ္စည်း
    0.28
    政府
    0.28
     onError
    0.28
     objectMapper
    0.28
     நிறுவனம்
    0.28
    DUNLAND
    0.27
     راستہ
    0.27
    NonUser
    0.27
    POSITIVE LOGITS
    6
    0.44
    0.41
    3
    0.38
    1
    0.37
    5
    0.37
    2
    0.36
    7
    0.36
    ish
    0.35
    8
    0.35
     até
    0.35
    Activations Density 0.346%

    No Known Activations