© 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. 145388
    Prev
    Next
    INDEX
    Explanations

    skin, beauty, body positioning

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

    creative stories

    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
    Decoration
    0.54
    Decorator
    0.51
    ut
    0.46
    Listening
    0.46
    A
    0.46
    utis
    0.46
    ler
    0.45
    Logger
    0.45
    ake
    0.45
    four
    0.45
    POSITIVE LOGITS
    事を
    0.54
    ᆹ
    0.52
     approached
    0.49
    撾
    0.47
     APPROACH
    0.44
    пка
    0.44
     anorexia
    0.44
    forcing
    0.44
     nrow
    0.43
    кы
    0.42
    Activations Density 0.000%

    No Known Activations