© 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. 47429
    Prev
    Next
    INDEX
    Explanations

    legal and policy terms

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

    repeat and practice actions

    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
     biopsies
    0.49
     biopsy
    0.46
    Stream
    0.44
     archive
    0.44
    Archive
    0.43
    מל
    0.43
     Archive
    0.42
    ל
    0.42
     Harper
    0.42
     transcriptome
    0.42
    POSITIVE LOGITS
    एनएस
    0.52
    drugs
    0.45
    INTa
    0.44
     بغیر
    0.43
    agents
    0.42
     aérea
    0.42
    horror
    0.42
     누구
    0.42
    ciencia
    0.42
    gruppen
    0.42
    Activations Density 0.001%

    No Known Activations