© 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. 95113
    Prev
    Next
    INDEX
    Explanations

    destruir, ruin, delete, overcome

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

    foreign language characters

    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
    <0xDB>
    0.55
    cliffe
    0.49
     caballero
    0.49
     года
    0.48
    species
    0.48
     গৃহে
    0.48
    ),"
    0.47
    ANDEZ
    0.47
     ולא
    0.46
    ")),
    0.46
    POSITIVE LOGITS
     apag
    0.45
     नष्ट
    0.45
    र्‍या
    0.44
    isph
    0.44
    ării
    0.44
    ت
    0.44
    我已经
    0.43
    ‘
    0.43
    ă
    0.43
     destruir
    0.42
    Activations Density 0.000%

    No Known Activations