© 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. 30780
    Prev
    Next
    INDEX
    Explanations

    breakdown and explanation

    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
     temas
    0.42
     restrictions
    0.41
     chromatin
    0.40
    SizeMode
    0.40
    ชค
    0.40
     နောက်
    0.40
    ϩ
    0.39
     fission
    0.39
     tougher
    0.39
     adat
    0.39
    POSITIVE LOGITS
    良好
    0.47
    Good
    0.45
    Certified
    0.43
    Y
    0.43
     দেখিলাম
    0.41
     Bewertung
    0.41
    अच्छ
    0.41
    AW
    0.41
     conveniente
    0.41
    絡
    0.40
    Activations Density 0.001%

    No Known Activations