© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130523
    Prev
    Next
    INDEX
    Explanations

    RAINN National Network

    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
    C
    0.40
    win
    0.40
     present
    0.38
     RAP
    0.37
    E
    0.37
    FRED
    0.37
    stat
    0.37
    CO
    0.36
    CR
    0.36
    デックス
    0.36
    POSITIVE LOGITS
     '#
    0.44
    नात्मक
    0.44
    婳
    0.43
     שמ
    0.42
     Пла
    0.40
    ළ
    0.40
     टाक
    0.40
     Notifications
    0.39
     roj
    0.39
    <unused2000>
    0.39
    Activations Density 0.005%

    No Known Activations