© 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. 211350
    Prev
    Next
    INDEX
    Explanations

    following specific phrases

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

    core features and strengths

    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
    ]^
    0.50
    目標
    0.46
    جار
    0.46
    푠
    0.43
    bted
    0.42
    OfYear
    0.41
    yson
    0.41
    jons
    0.40
    "^
    0.40
    prised
    0.39
    POSITIVE LOGITS
    ۔
    0.47
     das
    0.46
    产生
    0.45
     movimento
    0.45
     கழி
    0.45
    產生
    0.45
     پیسې
    0.45
     हल्के
    0.44
     müssen
    0.44
     mustn
    0.44
    Activations Density 0.000%

    No Known Activations