© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2410
    Prev
    Next
    INDEX
    Explanations

    cosine similarity

    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_all/layer_41_width_262k_l0_big
    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
     parcels
    0.50
     नल
    0.43
    テナ
    0.43
     precipitates
    0.42
    ിൽ
    0.42
     conjugates
    0.42
    ียบ
    0.42
    增
    0.42
     residues
    0.41
    یشن
    0.41
    POSITIVE LOGITS
    Cos
    1.09
    cos
    0.92
     cos
    0.92
     cosm
    0.92
     Cos
    0.91
     COSM
    0.87
     Cosm
    0.86
     Cosmo
    0.84
     kosm
    0.79
     cosine
    0.78
    Activations Density 0.003%

    No Known Activations