© 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. 108391
    Prev
    Next
    INDEX
    Explanations

    specifications and requirements

    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
     konular
    0.46
    彈
    0.46
     tendo
    0.44
     grafik
    0.44
    ancji
    0.44
     ㄱ
    0.44
     ndani
    0.43
    BEGIN
    0.43
    ので
    0.42
     검
    0.42
    POSITIVE LOGITS
     haunts
    0.46
    ToProps
    0.46
     hotspots
    0.44
     privados
    0.43
     Juz
    0.42
    édération
    0.41
     pity
    0.40
     buds
    0.40
    Favourites
    0.40
    ፍተኛ
    0.39
    Activations Density 0.005%

    No Known Activations