© 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. 84970
    Prev
    Next
    INDEX
    Explanations

    biologists, Service, private, sight, point

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

    convey the

    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
    राम
    0.58
    Outcome
    0.49
    र
    0.49
    For
    0.48
     Conversely
    0.47
    Control
    0.47
    ObjectMapper
    0.47
    Conflicts
    0.46
    स्क
    0.46
    紓
    0.45
    POSITIVE LOGITS
     microns
    0.55
     chefs
    0.52
     degrad
    0.52
     luxe
    0.50
     descendants
    0.50
     textural
    0.49
     biologists
    0.49
     deviant
    0.48
     zeer
    0.48
     enzym
    0.48
    Activations Density 0.015%

    No Known Activations