© 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. 101552
    Prev
    Next
    INDEX
    Explanations

    following specific words

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

    explaining dangerous areas

    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
    entrée
    0.54
     ἢ
    0.44
    SPRING
    0.44
    欧洲
    0.43
     LAMP
    0.43
     COURT
    0.42
     ಅಥವಾ
    0.42
    εδ
    0.42
    court
    0.41
    ফির
    0.41
    POSITIVE LOGITS
    ров
    0.50
    ▟
    0.45
    MiddleLine
    0.45
    "});
    0.43
     moldings
    0.43
     estimations
    0.42
     rheumatism
    0.42
     desesper
    0.42
    سط
    0.41
     tormented
    0.41
    Activations Density 0.003%

    No Known Activations