© 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. 133504
    Prev
    Next
    INDEX
    Explanations

    or potential, support, future, new

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

    understanding severe disease

    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
    ائیگی
    0.63
    룺
    0.54
    سوم
    0.51
    </bbox>
    0.50
    レッ
    0.50
    avkhat
    0.49
     جیک
    0.49
    اتی
    0.48
     واپ
    0.48
     فیصلے
    0.48
    POSITIVE LOGITS
    t
    0.53
     na
    0.50
    9
    0.49
    sensor
    0.46
    EST
    0.45
    version
    0.45
    i
    0.44
     Monday
    0.44
    nis
    0.43
    ,
    0.42
    Activations Density 0.001%

    No Known Activations