© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 14073
    Prev
    Next
    INDEX
    Explanations

    repetition is important

    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_65k_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
    و
    0.40
     одну
    0.39
     спро
    0.39
     cuarta
    0.38
    Traversal
    0.37
    }$).
    0.37
     вновь
    0.36
    MING
    0.36
    रण
    0.35
     داشت
    0.35
    POSITIVE LOGITS
     aquelas
    0.48
    𝐇
    0.46
     those
    0.45
    y
    0.44
    ,”
    0.44
    rà
    0.43
    
    0.42
    issimo
    0.41
     özellikleri
    0.41
     hel
    0.41
    Activations Density 0.049%

    No Known Activations