© 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. 128286
    Prev
    Next
    INDEX
    Explanations

    and instantly, and form, and optics

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

    lists, visual attributes, and risks

    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
    whom
    0.53
     whom
    0.52
    mming
    0.47
    ць
    0.45
    lder
    0.45
    Լ
    0.44
    li
    0.43
    До
    0.43
    liw
    0.42
    Р
    0.41
    POSITIVE LOGITS
     από
    0.50
     estándar
    0.44
    rát
    0.44
     kuitenkin
    0.44
    ,,
    0.43
     jt
    0.43
     maxLength
    0.43
    rneğin
    0.43
    ía
    0.43
     אם
    0.42
    Activations Density 0.000%

    No Known Activations