© 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. 73263
    Prev
    Next
    INDEX
    Explanations

    prayed for, simple opinion, course on

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

    protecting limits testing chains

    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
     dispel
    0.53
    ුණු
    0.50
    ᔪ
    0.49
     bús
    0.48
     formulate
    0.47
     proffered
    0.46
     MAGAZ
    0.46
     clasific
    0.46
     hasten
    0.46
     convincingly
    0.46
    POSITIVE LOGITS
    Ro
    0.50
    Το
    0.49
    Ed
    0.48
     Το
    0.46
    Πα
    0.46
    ح
    0.46
     ച
    0.45
    roc
    0.43
    LI
    0.42
    ards
    0.42
    Activations Density 0.000%

    No Known Activations