© 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. 14431
    Prev
    Next
    INDEX
    Explanations

    location and relationships

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

    programming and technical terms

    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
    mē
    0.49
    Reserve
    0.48
    薊
    0.47
    Your
    0.46
    makt
    0.46
     tipe
    0.46
    Substitute
    0.45
    였습니다
    0.45
    mese
    0.45
    Configure
    0.45
    POSITIVE LOGITS
     період
    0.47
     cocktails
    0.46
     Neck
    0.45
    ﻉ
    0.45
     charities
    0.45
     centers
    0.45
     शिवाय
    0.44
     arrays
    0.43
     grosses
    0.43
     Centers
    0.42
    Activations Density 0.000%

    No Known Activations