© 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. 141735
    Prev
    Next
    INDEX
    Explanations

    identify prospective

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

    very similar

    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
     ODDS
    0.47
    בו
    0.46
    據
    0.46
    場
    0.46
    de
    0.45
    ポジ
    0.45
    Seeds
    0.45
    Ud
    0.44
    土産
    0.44
    जि
    0.44
    POSITIVE LOGITS
     প্রত্যেক
    0.46
    :'',
    0.43
     '';
    0.43
     Identifier
    0.43
     가정
    0.43
     mỗi
    0.42
     liên
    0.42
     '*',
    0.41
     ArrayAdapter
    0.41
     Middleware
    0.41
    Activations Density 0.000%

    No Known Activations