© 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. 181046
    Prev
    Next
    INDEX
    Explanations

    reductions and glory

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

    maliciously, harmful ideologies, detrimental

    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
     pacific
    0.47
     unseen
    0.44
     gears
    0.44
    .
    0.44
     message
    0.43
     realities
    0.42
     expecting
    0.41
     gear
    0.40
     shades
    0.40
    RS
    0.39
    POSITIVE LOGITS
    Ꮺ
    0.49
     pénétr
    0.48
     συγκεκρι
    0.46
    ඪ
    0.45
    닼
    0.44
    мл
    0.43
    Посилання
    0.43
    校长
    0.43
     भ्र
    0.42
     மேலே
    0.42
    Activations Density 0.001%

    No Known Activations