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

    Neuronpedia

    Jacobian LensNEW
    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. 194676
    Prev
    Next
    INDEX
    Explanations

    code snippets and Go scaling

    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
    streamlit
    0.37
     processi
    0.37
     নারায়ণ
    0.37
    IFICATION
    0.36
    殉
    0.36
    になり
    0.35
    myLabels
    0.35
     ہمیں
    0.35
     Thursday
    0.34
    ோட
    0.34
    POSITIVE LOGITS
     ava
    0.43
    ==(
    0.43
    books
    0.42
    avam
    0.41
    erc
    0.39
     CORE
    0.38
     bounce
    0.38
     disponibilidade
    0.38
    CORE
    0.38
    athletics
    0.38
    Activations Density 0.000%

    No Known Activations