© 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. 74109
    Prev
    Next
    INDEX
    Explanations

    repeated offenses

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

    escape room, removal of ads, privilege

    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
    át
    0.44
    ux
    0.43
    anguage
    0.41
    件事情
    0.41
     jezik
    0.40
    ς
    0.40
    ik
    0.39
    aki
    0.39
    ánt
    0.39
    )";
    0.39
    POSITIVE LOGITS
     sayesinde
    0.52
     clic
    0.49
     despise
    0.48
     oppressive
    0.48
     Bege
    0.47
     loudest
    0.47
     Clique
    0.47
    ូន
    0.46
     كلكم
    0.46
     Senin
    0.46
    Activations Density 0.001%

    No Known Activations