© 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. 122624
    Prev
    Next
    INDEX
    Explanations

    official terms and descriptions

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

    got a / happened when / understand basic

    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
    y
    0.57
    o
    0.51
     ost
    0.47
    a
    0.46
    fraud
    0.46
    t
    0.46
    tarif
    0.45
    tiff
    0.45
    期間
    0.45
    防
    0.44
    POSITIVE LOGITS
     ፈ
    0.49
    aches
    0.48
    ى
    0.48
    칠
    0.47
    orphisms
    0.45
     thrice
    0.45
    وری
    0.45
     constitue
    0.45
     widow
    0.43
     sunscreen
    0.43
    Activations Density 0.000%

    No Known Activations