© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32005
    Prev
    Next
    INDEX
    Explanations

    continued, reduced, buildings, revelation, review, Birthday, number, download

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mensch
    0.48
    ҡ
    0.47
    dauer
    0.46
    gesamt
    0.46
    ҙ
    0.46
    InputNum
    0.46
     ఉపయోగ
    0.45
    SystemCall
    0.45
    CurrentImageData
    0.44
    પ્ત
    0.44
    POSITIVE LOGITS
    ائش
    0.48
     undergoes
    0.44
    ena
    0.44
    Fo
    0.44
     yh
    0.44
     Trademark
    0.43
     niveaux
    0.43
    𝗠
    0.42
     compressors
    0.42
     oure
    0.42
    Activations Density 0.001%

    No Known Activations