© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209406
    Prev
    Next
    INDEX
    Explanations

    unsolicited email

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

    structure enumeration

    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
    jection
    0.43
    iot
    0.41
    oles
    0.41
    lcd
    0.41
    cs
    0.40
    refixer
    0.40
    ヴ
    0.40
    junit
    0.40
    黜
    0.39
     jeweil
    0.39
    POSITIVE LOGITS
     Surprisingly
    0.51
     tais
    0.50
     conteúdo
    0.48
     WooCommerce
    0.46
     nasceu
    0.46
     NÃO
    0.46
    '||
    0.46
    نوان
    0.45
    、“
    0.44
    খানি
    0.44
    Activations Density 0.000%

    No Known Activations