© 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. 49654
    Prev
    Next
    INDEX
    Explanations

    self-referential actions

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

    harming yourself

    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
    自己的
    0.89
     ਆਪਣੇ
    0.84
     ਆਪਣ
    0.82
    নিজের
    0.80
    み
    0.80
     اپنا
    0.77
    下の
    0.76
    場合は
    0.75
     propias
    0.73
    実感
    0.73
    POSITIVE LOGITS
     I
    1.02
    -
    0.84
     X
    0.73
    p
    0.68
    ala
    0.64
    es
    0.63
     N
    0.63
    itt
    0.63
    o
    0.63
      
    0.62
    Activations Density 0.047%

    No Known Activations