© 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. 57084
    Prev
    Next
    INDEX
    Explanations

    flour, workouts, filler rod

    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
    ?
    0.43
    کار
    0.41
     környez
    0.41
     olmadan
    0.41
    ?!?
    0.40
     கமல்ஹா
    0.39
    ."
    0.38
    ?:
    0.38
    ?
    0.37
     Gente
    0.37
    POSITIVE LOGITS
    ushi
    0.42
     turmeric
    0.41
     supervisor
    0.41
    اؤ
    0.41
     challenge
    0.40
    ಿಲ್ಲ
    0.40
     obey
    0.40
     coward
    0.40
    nX
    0.40
    𝗷
    0.40
    Activations Density 0.004%

    No Known Activations