© 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. 240623
    Prev
    Next
    INDEX
    Explanations

    hajj

    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
    ievements
    0.44
    ksyon
    0.43
    Ys
    0.42
    ysen
    0.42
     இளைஞ
    0.42
    燊
    0.42
    倞
    0.42
    принима
    0.41
    берг
    0.41
    ikk
    0.41
    POSITIVE LOGITS
    in
    0.56
     in
    0.52
     Shown
    0.50
    i
    0.49
     shown
    0.46
     opposite
    0.46
    اؤ
    0.46
    safety
    0.46
     pitted
    0.46
    뜩
    0.46
    Activations Density 0.002%

    No Known Activations