© 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. 60398
    Prev
    Next
    INDEX
    Explanations

    here am I

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

    term, topic, exhibit, satellite, files

    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
    stev
    0.53
    ‏:‏
    0.52
    veli
    0.51
    वाँ
    0.49
    intero
    0.47
    mein
    0.47
    bestand
    0.47
    g
    0.46
    prüfung
    0.46
    :(
    0.46
    POSITIVE LOGITS
     pracy
    0.49
     consecutively
    0.48
     depositions
    0.46
     towards
    0.45
    ক্স
    0.44
     shingles
    0.43
     khối
    0.43
     เงิน
    0.43
     filings
    0.42
     ENTRE
    0.42
    Activations Density 0.000%

    No Known Activations