© 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. 69541
    Prev
    Next
    INDEX
    Explanations

    Puja special suggestions runs

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

    eye strain

    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
     बोल्ड
    0.50
    䡋
    0.46
    䢀
    0.46
    㝡
    0.45
     катастро
    0.45
    Ꮘ
    0.45
     Tattha
    0.44
     தென்
    0.44
     பயணி
    0.44
    薷
    0.44
    POSITIVE LOGITS
    ot
    0.59
    glasses
    0.48
    t
    0.47
    inn
    0.47
    \_
    0.47
    jc
    0.47
    in
    0.46
    ut
    0.46
    jamas
    0.46
    ac
    0.46
    Activations Density 0.000%

    No Known Activations