© 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. 162026
    Prev
    Next
    INDEX
    Explanations

    mode of data

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

    propagation concepts, flour, opportunity, readily, ranges

    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
    i
    0.55
    id
    0.52
    י
    0.51
    สอน
    0.50
     advices
    0.48
    шее
    0.45
    ié
    0.45
    illées
    0.44
     tenths
    0.44
    TEN
    0.43
    POSITIVE LOGITS
    撒
    0.56
    如下
    0.51
    濁
    0.47
    情
    0.43
     पाली
    0.42
     بح
    0.42
    dater
    0.42
    這一
    0.42
    他们的
    0.41
    靠近
    0.41
    Activations Density 0.000%

    No Known Activations