© 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. 191536
    Prev
    Next
    INDEX
    Explanations

    flags or labels

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

    secretive or ignoring legitimate

    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
    ة
    0.55
    -
    0.48
    uru
    0.46
    _
    0.46
    باً
    0.44
    ilian
    0.44
    ing
    0.44
    umpul
    0.44
    قة
    0.43
    }$=
    0.43
    POSITIVE LOGITS
     FLAGS
    0.56
     FLAG
    0.48
    FLAGS
    0.47
    FLAG
    0.47
     sebaik
    0.46
     izbor
    0.46
     मर्यादा
    0.46
    ママ
    0.46
     ulc
    0.46
    ಿಕ
    0.45
    Activations Density 0.001%

    No Known Activations