© 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. 135209
    Prev
    Next
    INDEX
    Explanations

    phrases introducing state or action

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

    destroy, want, especially

    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
    b
    0.55
    sø
    0.51
    u
    0.51
    besch
    0.50
    shows
    0.50
    pitch
    0.48
    bė
    0.48
    maps
    0.47
     जितने
    0.46
    })$;
    0.46
    POSITIVE LOGITS
    ИА
    0.49
     refriger
    0.49
    તન
    0.48
     bicarbon
    0.48
     Radeon
    0.45
     branco
    0.45
     topLeft
    0.44
     curved
    0.44
     diploma
    0.44
     видел
    0.44
    Activations Density 0.000%

    No Known Activations