© 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. 172473
    Prev
    Next
    INDEX
    Explanations

    risk assessments and monitoring agencies

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

    illustrates function concept

    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
    httparty
    0.55
    ᱓
    0.53
    jeto
    0.52
    jobj
    0.51
     Эль
    0.51
     слабы
    0.51
    bajo
    0.50
     mampu
    0.50
     Фургала
    0.50
     capaz
    0.49
    POSITIVE LOGITS
    ↵
    0.51
     Catch
    0.45
     Edwin
    0.45
     border
    0.44
     syn
    0.43
     illustration
    0.43
     Reggie
    0.43
     David
    0.42
     illust
    0.42
     '
    0.42
    Activations Density 0.000%

    No Known Activations