© 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. 174515
    Prev
    Next
    INDEX
    Explanations

    Mixing purchases

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

    database administrator

    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
     gradation
    0.49
     hlad
    0.44
    s
    0.43
    odob
    0.43
     reper
    0.43
    ковым
    0.42
    ಮಾಡ
    0.42
    ⠊
    0.41
     допо
    0.41
    гра
    0.41
    POSITIVE LOGITS
    emt
    0.50
    ino
    0.48
    Combination
    0.46
    ce
    0.46
    ige
    0.46
    Neither
    0.45
    Dried
    0.45
    retired
    0.45
    artige
    0.45
    Authentication
    0.44
    Activations Density 0.001%

    No Known Activations