© 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. 57305
    Prev
    Next
    INDEX
    Explanations

    quotation marks or special characters

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

    constants and arithmetic

    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
     bloco
    0.50
     quá
    0.47
    エリア
    0.46
     dados
    0.45
    :
    0.45
     título
    0.44
     belge
    0.44
     boek
    0.43
     detained
    0.43
    記事
    0.43
    POSITIVE LOGITS
    rat
    0.58
    yp
    0.56
    ön
    0.55
    𐰢
    0.53
    alignat
    0.52
    akarane
    0.52
    loat
    0.51
    nip
    0.51
    üte
    0.51
    ōs
    0.51
    Activations Density 0.000%

    No Known Activations