© 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. 17586
    Prev
    Next
    INDEX
    Explanations

    3rd ed

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

    technical requirements and code imports

    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
    멩
    0.51
    pieceSelection
    0.47
    imax
    0.46
     spinal
    0.44
     콘
    0.44
     imun
    0.43
     조정
    0.43
    amani
    0.42
    ndan
    0.42
     drawRight
    0.41
    POSITIVE LOGITS
    to
    0.49
    ರ
    0.47
    OutputStream
    0.47
     OutputStream
    0.45
    OutputPath
    0.44
    ISM
    0.44
    V
    0.43
     Baill
    0.43
    KS
    0.42
    Bru
    0.42
    Activations Density 0.000%

    No Known Activations