© 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. 231223
    Prev
    Next
    INDEX
    Explanations

    shall inherit

    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
    topology
    0.48
    renzia
    0.47
    Ō
    0.46
    kun
    0.46
    finale
    0.46
    haz
    0.45
     மய
    0.45
     הא
    0.45
    asing
    0.44
    faz
    0.44
    POSITIVE LOGITS
     eczema
    0.48
     możliwości
    0.46
    띠
    0.45
     uv
    0.43
     recours
    0.43
     UVB
    0.43
     logiciel
    0.43
     muitos
    0.42
     compañías
    0.42
     políticas
    0.42
    Activations Density 0.000%

    No Known Activations