© 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. 55005
    Prev
    Next
    INDEX
    Explanations

    uuids and alphanumeric identifiers

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

    GUIDs

    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
    িবার
    0.45
    ेलकम
    0.44
    顎
    0.44
    ម្ល
    0.43
     gamanam
    0.43
    ANGMAR
    0.43
    Grazie
    0.43
    branched
    0.42
    abhuto
    0.42
    Ketika
    0.41
    POSITIVE LOGITS
     –
    0.57
     Development
    0.54
     Characteristics
    0.51
     Extensions
    0.51
     Ext
    0.50
     Client
    0.49
     Person
    0.48
     Software
    0.48
     Opens
    0.48
     Enterprises
    0.48
    Activations Density 0.002%

    No Known Activations