© 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. 69776
    Prev
    Next
    INDEX
    Explanations

    phrase or word

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

    areas, days, research

    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
     fift
    0.50
     Eternity
    0.48
     Majesty
    0.48
     Maest
    0.45
     Solicitor
    0.44
     Garfield
    0.44
     Kig
    0.43
    き
    0.42
     SYN
    0.42
     Sister
    0.42
    POSITIVE LOGITS
    nless
    0.56
    ndrome
    0.54
    aid
    0.50
    elis
    0.49
    neum
    0.49
    ladder
    0.49
    lace
    0.49
    lastname
    0.48
    borough
    0.48
    barrier
    0.48
    Activations Density 0.000%

    No Known Activations