© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 197840
    Prev
    Next
    INDEX
    Explanations

    loan privacy parties voice

    np_acts-logits-general · gemini-2.5-flash-lite

    individual weaknesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    तपुर
    0.51
    टॉप
    0.50
     magia
    0.49
    <unused0>
    0.48
    法律
    0.47
     पाण्डेय
    0.47
     पांडेय
    0.46
     Monsters
    0.46
     caveats
    0.46
     निश्चय
    0.46
    POSITIVE LOGITS
    كم
    0.46
    рый
    0.41
    columnwidth
    0.41
     Voz
    0.40
     codimension
    0.40
    usstsein
    0.40
    (
    0.40
    process
    0.39
     \#
    0.39
    unlink
    0.39
    Activations Density 0.001%

    No Known Activations