© 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. 223451
    Prev
    Next
    INDEX
    Explanations

    category market related

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

    adhesive lining

    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
     अशी
    0.51
     로그인
    0.51
    रिमेंट
    0.49
    ठभे
    0.47
     MyRegisterClass
    0.46
    ט
    0.45
    𝗕
    0.45
    ड़की
    0.44
    rien
    0.44
    initWith
    0.44
    POSITIVE LOGITS
    u
    0.46
    algebra
    0.45
     dea
    0.45
     sina
    0.44
    pale
    0.44
    al
    0.41
    sina
    0.41
    liz
    0.41
     Telugu
    0.40
    innov
    0.40
    Activations Density 0.001%

    No Known Activations