© 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. 183919
    Prev
    Next
    INDEX
    Explanations

    sleep and rest

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

    life stages and relationships

    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
    TER
    0.46
    Little
    0.45
    Shows
    0.45
    }",
    0.44
    World
    0.42
    Arrays
    0.42
    Safe
    0.42
    }`,
    0.41
    생
    0.40
    Red
    0.40
    POSITIVE LOGITS
     contrace
    0.59
     pajamas
    0.58
     pique
    0.55
    IFORN
    0.54
     imprese
    0.54
     plaf
    0.54
     camar
    0.53
     pajama
    0.53
     partur
    0.52
     sequest
    0.52
    Activations Density 0.000%

    No Known Activations