© 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. 148948
    Prev
    Next
    INDEX
    Explanations

    online services and commerce

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

    social engineering and account investigation

    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
     истори
    0.46
    Це
    0.45
    మ్మ
    0.45
     figs
    0.45
    í
    0.45
    Ч
    0.44
     режи
    0.44
    т
    0.43
    ahanga
    0.43
     בית
    0.41
    POSITIVE LOGITS
    passion
    0.48
     signalé
    0.45
    riever
    0.44
    Passion
    0.44
    Conversely
    0.44
    ロップ
    0.43
     digitalen
    0.43
    torrent
    0.43
    lack
    0.43
    uert
    0.43
    Activations Density 0.000%

    No Known Activations