© 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. 191297
    Prev
    Next
    INDEX
    Explanations

    services, billed, fuel, crisis, surfaces

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

    Convolutional, heat, ice, upscale

    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
    INVISIBLE
    0.53
     ecologically
    0.49
     rango
    0.46
     Quỳnh
    0.45
     環
    0.45
    âne
    0.45
     xếp
    0.44
    ​—
    0.44
     senang
    0.44
     đánh
    0.43
    POSITIVE LOGITS
    ه
    0.55
    a
    0.51
    Cf
    0.47
    ఒ
    0.46
     میٹر
    0.45
    هام
    0.44
    SI
    0.44
    i
    0.44
    Kamp
    0.44
    Alle
    0.43
    Activations Density 0.000%

    No Known Activations