© 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. 157679
    Prev
    Next
    INDEX
    Explanations

    get your

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

    potential consequences of actions

    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
    categorie
    0.49
     développ
    0.47
    ૂત
    0.46
     économique
    0.46
    ülő
    0.46
    ándose
    0.46
    lán
    0.46
    喹
    0.45
    èrent
    0.45
    ření
    0.45
    POSITIVE LOGITS
    K
    0.51
    _
    0.50
    🉐
    0.50
     relieved
    0.49
     Bikini
    0.49
     Shout
    0.49
     Pentagon
    0.48
    "]
    0.48
    เยี่ยม
    0.48
     Syllabus
    0.48
    Activations Density 0.000%

    No Known Activations