© 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. 67148
    Prev
    Next
    INDEX
    Explanations

    looking for a

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

    speech_recognition, symbols, byte offset

    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
    Heather
    0.52
    製品
    0.51
    パナソニック
    0.49
    Jenn
    0.47
    لاست
    0.47
    膚
    0.47
     vendedores
    0.46
    ઓ
    0.46
     preços
    0.45
    Hearing
    0.45
    POSITIVE LOGITS
    halte
    0.50
    ening
    0.49
    sequent
    0.49
    gres
    0.48
     dź
    0.47
    hift
    0.47
    iser
    0.46
    isiin
    0.46
    iblock
    0.45
     PGA
    0.44
    Activations Density 0.000%

    No Known Activations