© 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. 41-GEMMASCOPE-2-RES-262K
    7. 2921
    Prev
    Next
    INDEX
    Explanations

    open source weights

    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_all/layer_41_width_262k_l0_big
    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
    orphic
    0.52
     infallible
    0.50
     rhythmic
    0.49
    適用
    0.49
    )$;
    0.48
     triglyceride
    0.47
     noirâtres
    0.47
    滌
    0.47
    対処
    0.47
    تيب
    0.47
    POSITIVE LOGITS
    开源
    1.31
     open
    1.20
    开放
    1.20
    open
    1.15
    Open
    1.13
     openness
    1.13
     Open
    1.12
    開放
    1.06
     오픈
    1.02
    オープン
    0.96
    Activations Density 0.010%

    No Known Activations