© 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. 199572
    Prev
    Next
    INDEX
    Explanations

    inhuman and creepy

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

    ethical considerations and warnings

    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
    खाना
    0.48
     secre
    0.46
    ESSAGE
    0.46
     하지만
    0.46
    하지만
    0.44
     découvre
    0.44
    ڏ
    0.44
     sdx
    0.43
     кантора
    0.42
     فونیټ
    0.42
    POSITIVE LOGITS
     बाली
    0.48
     दस
    0.46
    挚
    0.46
    蜒
    0.45
     अक्ष
    0.44
     inhuman
    0.44
    ween
    0.44
     уверен
    0.44
     creepy
    0.43
     средне
    0.43
    Activations Density 0.001%

    No Known Activations