© 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. 204468
    Prev
    Next
    INDEX
    Explanations

    foreign documents, your website, succeed in

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

    salvation, current, stations, now

    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
     ተግባ
    0.55
     (-)
    0.52
    ClearedBy
    0.52
    ტორი
    0.51
     dô
    0.50
     concealment
    0.50
     საშ
    0.49
     Watering
    0.49
     gardener
    0.49
     waarde
    0.49
    POSITIVE LOGITS
    Q
    0.57
    9
    0.56
    2
    0.54
    5
    0.54
    8
    0.52
    Η
    0.49
    Α
    0.47
    З
    0.47
    anno
    0.47
    7
    0.47
    Activations Density 0.000%

    No Known Activations