© 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. 170256
    Prev
    Next
    INDEX
    Explanations

    "gift", "required", "expensive"

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

    explaining origins and value proposition

    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
    is
    0.57
    as
    0.53
    would
    0.53
     surm
    0.52
    m
    0.51
    ova
    0.50
    cles
    0.50
    be
    0.49
    it
    0.48
    ed
    0.47
    POSITIVE LOGITS
     पृष्ठभूमि
    0.49
    "]).
    0.48
    ]).
    0.48
     خاطر
    0.46
     rokov
    0.46
     અથવા
    0.46
    četně
    0.46
     consecutivos
    0.46
     Hintergrund
    0.46
     بڑی
    0.45
    Activations Density 0.001%

    No Known Activations