© 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. 48502
    Prev
    Next
    INDEX
    Explanations

    occasions that, actually running

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

    open-minded female

    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
    Roll
    0.53
    ROLL
    0.51
    𝗡
    0.49
    áním
    0.48
    P
    0.48
    制造业
    0.48
    RI
    0.48
    Pull
    0.47
    NAB
    0.47
    피
    0.46
    POSITIVE LOGITS
     solicitudes
    0.51
     operasi
    0.50
     acog
    0.50
     necesarias
    0.49
     sudah
    0.49
     condiciones
    0.48
     criterios
    0.48
     embryos
    0.48
     collaborations
    0.47
     collaborators
    0.47
    Activations Density 0.000%

    No Known Activations