© 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. 222333
    Prev
    Next
    INDEX
    Explanations

    phrases ending in specific tokens

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

    technical identifiers and terms

    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
    кона
    0.53
    𒅗
    0.50
    蟆
    0.49
    IENCE
    0.48
     acuity
    0.48
     پاب
    0.48
     livros
    0.47
     অভিনন্দন
    0.47
    𐰴
    0.47
     résoudre
    0.46
    POSITIVE LOGITS
    ませ
    0.47
     MB
    0.42
    ii
    0.42
     mercedes
    0.40
    ☛
    0.39
    grpc
    0.38
    log
    0.38
     প্রথমে
    0.38
    iii
    0.38
     ECC
    0.37
    Activations Density 0.000%

    No Known Activations