© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3752
    Prev
    Next
    INDEX
    Explanations

    class definitions, constructor, this, self

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ן
    0.63
    ang
    0.62
    um
    0.60
    n
    0.58
    )
    0.57
    ah
    0.55
    _
    0.55
    t
    0.51
    ian
    0.50
    ↵
    0.49
    POSITIVE LOGITS
    ב
    0.48
    ١
    0.47
    0.47
     связан
    0.45
    🦦
    0.45
    коном
    0.44
    ológicas
    0.44
     químicas
    0.43
    ों
    0.43
     gustaría
    0.42
    Activations Density 0.026%

    No Known Activations