© 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. 186396
    Prev
    Next
    INDEX
    Explanations

    book too

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

    instructions to read through these

    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
    0.51
    Div
    0.48
    Kam
    0.48
    2
    0.47
    STAND
    0.46
    KAM
    0.46
    Lloyd
    0.45
    ቃ
    0.44
    HALL
    0.44
    Hall
    0.43
    POSITIVE LOGITS
     clearContext
    0.49
     crebre
    0.48
     idE
    0.48
     dọc
    0.47
    athletics
    0.47
     पाओ
    0.46
    .\
    0.46
     esigen
    0.46
    怸
    0.46
    \},\{
    0.46
    Activations Density 0.000%

    No Known Activations