© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84905
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing states

    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_40_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
    움을
    0.40
     hacks
    0.39
     Ausstellung
    0.39
    ংলার
    0.38
     instants
    0.38
     wówczas
    0.38
    懼
    0.37
    သုံး
    0.37
     daga
    0.37
    貸款
    0.37
    POSITIVE LOGITS
    reset
    0.45
    Mapping
    0.44
     consciously
    0.43
    ﾘ
    0.43
    +(
    0.42
     reset
    0.42
    րա
    0.41
     comfortably
    0.39
    Theater
    0.39
    lewati
    0.39
    Activations Density 0.000%

    No Known Activations