© 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. 31795
    Prev
    Next
    INDEX
    Explanations

    on the

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

    technical and specific terms

    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
     taylor
    0.54
    }\\
    0.49
     }\
    0.48
     "]
    0.46
     আটক
    0.46
     \\
    0.46
     Taylor
    0.46
     Display
    0.45
    +(-
    0.45
     Mfg
    0.45
    POSITIVE LOGITS
     Ан
    0.52
    '
    0.52
    嚩
    0.49
    ettre
    0.48
     rises
    0.45
     лежит
    0.45
    인다
    0.45
    URE
    0.44
    extension
    0.44
    embeddings
    0.44
    Activations Density 0.001%

    No Known Activations