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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50907
    Prev
    Next
    INDEX
    Explanations

    understanding the why

    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
     μεγά
    0.46
     Mainly
    0.44
     ထ
    0.44
     suffisamment
    0.43
    主に
    0.43
     सच्ची
    0.42
     যেসব
    0.42
     পরমাণ
    0.42
     보호
    0.41
     συγκεκρι
    0.40
    POSITIVE LOGITS
    ر
    0.46
    ategor
    0.45
     dispon
    0.44
     simplistic
    0.44
    लेशन
    0.43
     year
    0.42
     basit
    0.41
     आपका
    0.41
     willpower
    0.41
    ר
    0.41
    Activations Density 0.015%

    No Known Activations