© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 131376
    Prev
    Next
    INDEX
    Explanations

    own server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     партне
    0.45
    銛
    0.42
     недостатки
    0.42
    濃度
    0.40
    ⓡ,
    0.40
     कैफ
    0.40
     აღმასრულ
    0.40
     பேரும்
    0.40
     иденти
    0.39
    Amen
    0.38
    POSITIVE LOGITS
    emp
    0.44
     [[
    0.42
    iously
    0.41
    ......
    0.39
     W
    0.38
    uberculosis
    0.38
    किन
    0.38
    ...
    0.38
    ürich
    0.37
    ennie
    0.37
    Activations Density 0.000%

    No Known Activations