© 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. 38108
    Prev
    Next
    INDEX
    Explanations

    post requests, series parallels

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

    places and activities

    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
    א
    0.51
    akespe
    0.47
     वगैरह
    0.47
     détermine
    0.45
     முதலிய
    0.45
    愆
    0.45
     ಔಷ
    0.44
     hâ
    0.44
    遗传
    0.44
     posteriores
    0.43
    POSITIVE LOGITS
     tourism
    0.49
     शानदार
    0.48
    মনের
    0.45
     showrooms
    0.45
     picnics
    0.43
    銀座
    0.42
     ping
    0.42
     residents
    0.41
     brine
    0.41
     sumptuous
    0.41
    Activations Density 0.000%

    No Known Activations