© 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. 190951
    Prev
    Next
    INDEX
    Explanations

    Windows system paths

    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
    䄱
    0.38
    원을
    0.37
    パターン
    0.37
     ESP
    0.36
    dagger
    0.36
    mana
    0.36
    零
    0.35
    こちら
    0.34
    בוד
    0.34
     negate
    0.34
    POSITIVE LOGITS
    гей
    0.42
     폭
    0.39
     Squirrel
    0.39
     পর্
    0.38
    振り
    0.38
     हराया
    0.37
    hacking
    0.37
     sylvis
    0.37
    ᒥ
    0.36
    ಪಾ
    0.36
    Activations Density 0.001%

    No Known Activations