© 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. 115958
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and sentiment

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

    accept and value

    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
    Encode
    0.51
    仮
    0.44
    hattan
    0.44
    }(
    0.43
    ﻔ
    0.43
    LEC
    0.43
    ahara
    0.42
    Inspector
    0.42
     حمایت
    0.42
    ق
    0.42
    POSITIVE LOGITS
     lou
    0.52
    muy
    0.47
     großer
    0.47
     sweeter
    0.45
     broadened
    0.45
     glad
    0.43
     heureux
    0.43
     leps
    0.43
     Luxurious
    0.43
     wieder
    0.43
    Activations Density 0.001%

    No Known Activations