© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63069
    Prev
    Next
    INDEX
    Explanations

    corner and corners

    np_acts-logits-general · gemini-2.5-flash-lite

    corner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hairs
    0.46
    隧
    0.46
    لاث
    0.45
    tunnel
    0.45
    籶
    0.44
     tunnels
    0.44
    ظر
    0.44
    Lesson
    0.44
    ।,
    0.44
    عيه
    0.43
    POSITIVE LOGITS
     corner
    1.58
    corner
    1.47
     corners
    1.41
    Corner
    1.40
     Corner
    1.38
     esquina
    1.23
     Corners
    1.22
     कोने
    1.20
    corners
    1.16
    角
    1.12
    Activations Density 0.046%

    No Known Activations