© 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. 1981
    Prev
    Next
    INDEX
    Explanations

    potential risks or consequences

    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
    াক্রমে
    0.35
    ከላከ
    0.32
     桌
    0.30
    璘
    0.30
     previamente
    0.30
     നേര
    0.29
    加えて
    0.29
    对应的
    0.28
    abilité
    0.28
    糈
    0.27
    POSITIVE LOGITS
     pharmac
    0.34
     doctors
    0.32
    sc
    0.31
    pharmac
    0.31
     hypotension
    0.31
     theoretically
    0.31
     M
    0.30
     he
    0.30
    script
    0.30
     surgeon
    0.30
    Activations Density 0.000%

    No Known Activations