© 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. 25172
    Prev
    Next
    INDEX
    Explanations

    list manipulation and procedures

    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
    jš
    0.49
    ifestyle
    0.48
    ӱ
    0.48
    aş
    0.48
    ros
    0.48
    intérêt
    0.46
    ∑</
    0.45
     ശാ
    0.45
    ि
    0.45
    scri
    0.45
    POSITIVE LOGITS
     Quel
    0.52
     Moi
    0.51
     VPC
    0.50
     одним
    0.50
     VT
    0.49
     опы
    0.48
     NE
    0.48
     Kahn
    0.48
     NPR
    0.48
     MLP
    0.48
    Activations Density 0.004%

    No Known Activations