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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224081
    Prev
    Next
    INDEX
    Explanations

    lists of actions

    np_acts-logits-general · gemini-2.5-flash-lite

    role and subsequent context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OWN
    0.50
     ধৈ
    0.50
    Isn
    0.49
    勂
    0.48
    血压
    0.48
     যের
    0.47
    ICK
    0.44
     ধৈর্য
    0.44
     製造
    0.44
     সান
    0.44
    POSITIVE LOGITS
     late
    0.46
     nine
    0.45
     لی
    0.45
     midnight
    0.45
    ეთი
    0.44
     mediating
    0.42
     Förderung
    0.42
     combating
    0.42
    :“
    0.42
     pada
    0.41
    Activations Density 0.000%

    No Known Activations