© 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. 53-GEMMASCOPE-2-RES-262K
    4. 166976
    Prev
    Next
    INDEX
    Explanations

    verbs of change: adjust, changed

    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_53_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
     intelligible
    0.41
    sein
    0.41
    鹭
    0.40
     clogging
    0.39
     delights
    0.38
     refreshToken
    0.38
     bumper
    0.38
     !!,
    0.38
     keel
    0.38
     penny
    0.37
    POSITIVE LOGITS
    slave
    0.41
    aji
    0.38
    io
    0.38
     G
    0.36
    idi
    0.36
    AV
    0.36
    ஜி
    0.36
    AI
    0.35
    rough
    0.35
    ai
    0.34
    Activations Density 0.000%

    No Known Activations