© 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. 53-GEMMASCOPE-2-RES-262K
    7. 85949
    Prev
    Next
    INDEX
    Explanations

    code documentation and explanations

    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_53_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
    בוה
    0.42
    FAPI
    0.40
    ంతో
    0.39
    PasswordField
    0.38
    ಿಣ
    0.37
    <unused339>
    0.36
    縞
    0.36
    orderHint
    0.36
    ＞
    0.35
     खुशख
    0.35
    POSITIVE LOGITS
     $(\
    0.42
    <b>
    0.37
    <u>
    0.36
    hrs
    0.35
    nis
    0.35
    ナス
    0.35
     😂
    0.34
    inten
    0.34
     hrs
    0.33
    don
    0.33
    Activations Density 10.135%

    No Known Activations