© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51222
    Prev
    Next
    INDEX
    Explanations

    understanding what's happening

    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
    UGH
    0.43
    requent
    0.42
     sm
    0.42
     joking
    0.40
    ‪
    0.40
    ⁍
    0.39
    ikai
    0.39
    クリル
    0.39
    <
    0.38
     tubs
    0.38
    POSITIVE LOGITS
    ભાવ
    0.58
     Règlement
    0.49
     Chaque
    0.48
     എഴു
    0.47
     விசார
    0.46
     parfaite
    0.46
     பணிகள்
    0.46
    ıc
    0.45
     botanique
    0.45
     Grenzen
    0.45
    Activations Density 0.003%

    No Known Activations