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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111703
    Prev
    Next
    INDEX
    Explanations

    joining the, playable, little

    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
     хочется
    0.49
     h
    0.46
     threatens
    0.46
     tehd
    0.46
     rhe
    0.45
     indik
    0.45
     eer
    0.45
     lagi
    0.44
     Puis
    0.43
     ervan
    0.43
    POSITIVE LOGITS
    ophyte
    0.50
    리아
    0.44
    라인
    0.43
    eline
    0.43
    리
    0.43
    ても
    0.42
    methanol
    0.41
    ոչ
    0.41
    엣
    0.41
    obacterium
    0.41
    Activations Density 0.006%

    No Known Activations