© 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. 105694
    Prev
    Next
    INDEX
    Explanations

    find or spraying

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

    more Python

    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
     °
    0.47
     multic
    0.46
     poly
    0.44
    0.43
     Institutional
    0.43
     institutional
    0.42
     subsequence
    0.42
     D
    0.41
     postcard
    0.40
     transitional
    0.40
    POSITIVE LOGITS
    íamos
    0.53
     numar
    0.53
     المقدم
    0.52
     сосре
    0.52
    BURTS
    0.50
    ACION
    0.50
    ਕਾਰੀ
    0.50
    စျေး
    0.50
    ímos
    0.50
     అయిన
    0.49
    Activations Density 0.003%

    No Known Activations