© 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. 47134
    Prev
    Next
    INDEX
    Explanations

    crest detailing

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

    search engine commands

    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
     vele
    0.53
     patru
    0.47
    Anomaly
    0.46
     vijf
    0.45
    к
    0.44
     idag
    0.43
     ró
    0.43
     treb
    0.42
     langit
    0.42
    ย
    0.41
    POSITIVE LOGITS
    children
    0.47
     conditioned
    0.46
     家
    0.45
     fractured
    0.44
    धपुर
    0.44
     കുട്ട
    0.44
    čiť
    0.44
     henkil
    0.43
     hvert
    0.43
     เรียน
    0.43
    Activations Density 0.000%

    No Known Activations