© 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. 137248
    Prev
    Next
    INDEX
    Explanations

    information processing

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

    descriptive historical or functional phrases

    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
    –
    0.45
    maxim
    0.43
     bilingual
    0.43
    playback
    0.43
     Leon
    0.41
     Andrade
    0.41
    whitespace
    0.41
     pandemia
    0.41
    Maxim
    0.40
    widths
    0.40
    POSITIVE LOGITS
    假設
    0.46
     बच्‍चे
    0.44
    子的
    0.43
    Ử
    0.43
    的信息
    0.43
    zyloxy
    0.43
    ॉफ्ट
    0.42
    诣
    0.41
    ദം
    0.41
     учун
    0.40
    Activations Density 0.002%

    No Known Activations