© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44412
    Prev
    Next
    INDEX
    Explanations

    find safety or prevent danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    祚
    0.45
    тор
    0.45
    рис
    0.44
    с
    0.44
     conect
    0.42
    тивность
    0.42
    Carpenter
    0.41
     reale
    0.41
     hrane
    0.40
     magick
    0.39
    POSITIVE LOGITS
    ISON
    0.45
    jším
    0.44
    K
    0.44
     कोण
    0.43
     छुट्टी
    0.43
     ਨ
    0.42
     �
    0.42
    azos
    0.42
    เหมาะ
    0.41
    jších
    0.41
    Activations Density 0.002%

    No Known Activations