© 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. 60340
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated terms

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

    successful phrasing

    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
     glitch
    0.49
     outsourcing
    0.49
     alright
    0.47
    \%,
    0.46
     errore
    0.45
     aligned
    0.45
    izophren
    0.45
     echocardi
    0.45
     twists
    0.45
     amminist
    0.45
    POSITIVE LOGITS
     своего
    0.52
     خالد
    0.48
     позволяют
    0.47
     наших
    0.46
    ك
    0.46
    Apollo
    0.46
    =""><
    0.45
    丙基
    0.44
     зале
    0.44
    闌
    0.44
    Activations Density 0.000%

    No Known Activations