© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44194
    Prev
    Next
    INDEX
    Explanations

    urgency, action, 'really', 'not', 'cognitive'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     lông
    0.86
     Playboy
    0.85
    й
    0.79
    джа
    0.77
    woorden
    0.77
    াস্থ্য
    0.76
    咖啡
    0.76
    肽
    0.76
     géographique
    0.75
    fungsi
    0.74
    POSITIVE LOGITS
    ${
    0.88
     not
    0.86
    an
    0.80
    SW
    0.79
    FS
    0.78
    am
    0.74
    k
    0.74
    }
    0.72
     TWO
    0.71
    <
    0.71
    Activations Density 0.000%

    No Known Activations