© 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. 137451
    Prev
    Next
    INDEX
    Explanations

    Save, Continue, weddings, rules, market

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

    acknowledges, reminds, saving

    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
     कुलपति
    0.52
    apabb
    0.52
     trabalhando
    0.49
    йдз
    0.47
    orkel
    0.47
     functionals
    0.47
    jasama
    0.47
    ᱮ
    0.46
     passeio
    0.46
    ਫ਼
    0.46
    POSITIVE LOGITS
    ’
    0.47
    UP
    0.46
     图片
    0.46
     Proof
    0.45
     Images
    0.44
    TE
    0.44
    -
    0.44
    </
    0.43
     Anda
    0.42
    Референце
    0.42
    Activations Density 0.000%

    No Known Activations