© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    price range and descriptors

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

    `attraction` `changes` `Impact`

    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
    و
    0.51
    Kane
    0.50
    де
    0.49
    س
    0.49
    Selon
    0.49
    OutOf
    0.48
    );
    0.48
    Runtime
    0.48
    WARN
    0.48
    GetData
    0.48
    POSITIVE LOGITS
    病院
    0.50
    ayers
    0.50
     breaching
    0.49
     breached
    0.47
     volleyball
    0.47
     newspapers
    0.46
    酢
    0.46
    vertebr
    0.44
     Managers
    0.43
     bakter
    0.43
    Activations Density 0.000%

    No Known Activations