© 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. 100416
    Prev
    Next
    INDEX
    Explanations

    changes until

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

    sunlight and shadows

    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
    い
    0.50
     kepentingan
    0.47
    艶
    0.46
    Persona
    0.46
    Produto
    0.44
     samband
    0.44
    ﺴ
    0.44
    市場
    0.42
    似
    0.42
     creando
    0.41
    POSITIVE LOGITS
    ASSERT
    0.47
     Digests
    0.47
     Dink
    0.47
     hinted
    0.46
     स्ट्रीट
    0.46
     itch
    0.45
     huddled
    0.45
     Chen
    0.44
     प्लेट
    0.44
    гут
    0.44
    Activations Density 0.000%

    No Known Activations