© 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. 31309
    Prev
    Next
    INDEX
    Explanations

    app design or functionality

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

    Boolean indicating presence

    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
    ₎
    0.55
     தன்மை
    0.52
    ㅈ
    0.50
     يت
    0.49
     పదార్థ
    0.48
     忄
    0.48
    portions
    0.48
    excludes
    0.48
     बत्रा
    0.48
    ﺏ
    0.48
    POSITIVE LOGITS
     on
    0.45
    ilde
    0.44
    ordo
    0.44
    eware
    0.44
     fully
    0.43
     privilege
    0.43
     able
    0.43
     høj
    0.43
     hands
    0.42
     vertrou
    0.42
    Activations Density 0.000%

    No Known Activations