© 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. 165759
    Prev
    Next
    INDEX
    Explanations

    linger long

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

    hair thinning, grayish, evaporation

    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
    aciones
    0.51
    зку
    0.46
    зал
    0.45
    _{,
    0.44
    贷
    0.44
    
    0.43
     neuesten
    0.43
    ျ
    0.42
    yste
    0.42
    <0xBC>
    0.41
    POSITIVE LOGITS
    nav
    0.49
     donn
    0.47
    트는
    0.47
    डो
    0.46
    tid
    0.45
     Chowdh
    0.45
    jih
    0.44
    araja
    0.44
     Mubarak
    0.44
    t
    0.44
    Activations Density 0.001%

    No Known Activations