© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20696
    Prev
    Next
    INDEX
    Explanations

    driving, dosage, central, cordless, credit, female, financial

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

    chord names and lyrics

    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
    <unused64>
    0.42
    鳖
    0.40
     ভোটে
    0.40
    remia
    0.39
     انتخابات
    0.39
    ađ
    0.38
    鱉
    0.38
     altro
    0.38
     baloncesto
    0.38
    ắ
    0.38
    POSITIVE LOGITS
    ↵↵
    0.44
    ',
    0.41
    再次
    0.41
    ,
    0.41
     다시
    0.40
     —
    0.39
     —,
    0.38
    ,}
    0.37
    —
    0.37
     Price
    0.37
    Activations Density 0.025%

    No Known Activations