© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29927
    Prev
    Next
    INDEX
    Explanations

    specific noun-verb pairings

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

    face vitamines and vitamin c

    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
    w
    0.50
    were
    0.49
    /
    0.47
    7
    0.46
    high
    0.45
     on
    0.45
    —
    0.45
    HEP
    0.45
    existence
    0.44
    God
    0.44
    POSITIVE LOGITS
    textColour
    0.46
    敺
    0.45
     ottobre
    0.44
    রদ্ব
    0.44
     বলিউ
    0.44
    entuk
    0.43
     अा
    0.43
    olazione
    0.43
    ửi
    0.42
     nuestra
    0.42
    Activations Density 0.000%

    No Known Activations