© 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. 242979
    Prev
    Next
    INDEX
    Explanations

    noun endings and descriptive words

    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
    rna
    0.51
     меж
    0.50
     dragonfly
    0.50
     п
    0.47
     جر
    0.47
     অভিযান
    0.47
     გამოყენ
    0.45
     sesu
    0.45
     przeb
    0.45
     registra
    0.45
    POSITIVE LOGITS
    ANY
    0.48
    DIS
    0.45
    varage
    0.45
    레
    0.45
    DES
    0.44
    iy
    0.44
    THIS
    0.44
    攸
    0.43
    Whenever
    0.43
    THERE
    0.43
    Activations Density 0.001%

    No Known Activations