© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166715
    Prev
    Next
    INDEX
    Explanations

    lists and specific contexts

    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_40_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
    ার্থ
    0.44
    रिया
    0.39
    壴
    0.36
    遊び
    0.36
     лам
    0.36
     lamb
    0.36
     lambda
    0.35
    ランプ
    0.35
     carpet
    0.35
     PAY
    0.35
    POSITIVE LOGITS
    iorum
    0.42
    Five
    0.40
     Five
    0.40
    igare
    0.40
    部分的
    0.39
    pung
    0.39
    ündung
    0.38
     ponds
    0.38
    谚
    0.38
     מער
    0.37
    Activations Density 0.000%

    No Known Activations