© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75127
    Prev
    Next
    INDEX
    Explanations

    RPG specific quirks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isometric
    0.46
    䚰
    0.46
     정리
    0.46
    ்டோ
    0.46
    百年
    0.45
    bicyclo
    0.45
    μένου
    0.42
     caricature
    0.42
    기도
    0.42
    舢
    0.42
    POSITIVE LOGITS
    ä
    0.49
     is
    0.48
     Ö
    0.48
    iti
    0.48
     must
    0.47
    вается
    0.47
    tp
    0.47
    1
    0.47
    änd
    0.47
    Ä
    0.47
    Activations Density 0.001%

    No Known Activations