© 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. 159626
    Prev
    Next
    INDEX
    Explanations

    custom bike

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

    AI and safety guidelines

    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
     solvent
    0.47
    >
    0.46
     mainstream
    0.46
     polysaccharides
    0.44
     strugg
    0.43
     synthes
    0.43
    ords
    0.42
    ż
    0.42
    seq
    0.42
     catalysis
    0.41
    POSITIVE LOGITS
    덩
    0.47
    和谐
    0.46
    علي
    0.45
    нің
    0.44
    Dale
    0.42
    朳
    0.41
     материалов
    0.41
    賢
    0.41
    μός
    0.41
    ERIC
    0.41
    Activations Density 0.001%

    No Known Activations