© 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. 19525
    Prev
    Next
    INDEX
    Explanations

    word pairings

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

    of followed by nouns or numbers

    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
     centroids
    0.44
    Ꮡ
    0.44
    ൮
    0.44
    рами
    0.43
    ROCK
    0.42
    स्कृत
    0.41
    ઋ
    0.41
    Precio
    0.40
    语文
    0.40
    烔
    0.40
    POSITIVE LOGITS
    ce
    0.38
    ŋ
    0.37
    withdraw
    0.37
    difference
    0.36
    seriously
    0.35
    accord
    0.35
     Byron
    0.35
     அனை
    0.34
    wild
    0.34
    ute
    0.34
    Activations Density 0.000%

    No Known Activations