© 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. 112718
    Prev
    Next
    INDEX
    Explanations

    enlightened stores

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

    systems and policies

    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
     அழைத்து
    0.51
    uela
    0.50
     þing
    0.49
     tivesse
    0.49
    ientôt
    0.49
    穵
    0.48
     Piso
    0.47
     uitgenodigd
    0.47
     повинні
    0.47
     ಸಂಗೀತ
    0.47
    POSITIVE LOGITS
    MA
    0.50
    expression
    0.48
    N
    0.48
    ANY
    0.48
    短
    0.48
    AL
    0.47
    w
    0.47
    csp
    0.45
    L
    0.45
    RC
    0.44
    Activations Density 0.000%

    No Known Activations