© 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. 101610
    Prev
    Next
    INDEX
    Explanations

    altered states

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

    ability at, binds to, expression in

    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
     hims
    0.49
    つつ
    0.48
    ည
    0.48
    基づ
    0.47
    ご
    0.47
    孰
    0.46
    ра
    0.46
    ウェ
    0.45
     پیسې
    0.45
    xadmin
    0.44
    POSITIVE LOGITS
     for
    0.55
    ühle
    0.53
     komme
    0.53
     natur
    0.52
     stort
    0.52
     diuretic
    0.50
     metode
    0.50
     klasse
    0.50
     lä
    0.48
    ynch
    0.48
    Activations Density 0.000%

    No Known Activations