© 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. 237739
    Prev
    Next
    INDEX
    Explanations

    tested, guaranteed, recommended, capability

    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
    └
    0.48
     después
    0.46
     visitas
    0.46
     iniciativas
    0.46
     dun
    0.45
     torneo
    0.45
     começando
    0.45
     visites
    0.44
    ੀ
    0.44
    前景
    0.44
    POSITIVE LOGITS
     ప్రమా
    0.49
    ual
    0.47
     competence
    0.47
    uals
    0.46
    lems
    0.43
     hmot
    0.43
     gravitation
    0.42
    istungs
    0.42
    capability
    0.42
    ually
    0.40
    Activations Density 0.003%

    No Known Activations