© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 35758
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
    阐
    0.46
    覦
    0.44
    ेशन
    0.42
    ობა
    0.42
     сложно
    0.41
    叅
    0.40
    闡
    0.40
    会议
    0.40
     konfer
    0.40
    谦
    0.40
    POSITIVE LOGITS
    ci
    0.55
    cl
    0.51
    ri
    0.50
    M
    0.50
    ad
    0.49
    kao
    0.49
    v
    0.47
    q
    0.47
    is
    0.47
     accred
    0.46
    Activations Density 0.006%

    No Known Activations