© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226172
    Prev
    Next
    INDEX
    Explanations

    preposition followed by a verb or noun

    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
    基本上
    0.49
    ारण
    0.49
    ंता
    0.46
     nutric
    0.46
     photographic
    0.45
    膚
    0.44
     tais
    0.44
     talento
    0.44
    уна
    0.43
     culminating
    0.42
    POSITIVE LOGITS
    Id
    0.47
    Adresse
    0.46
     immunoprec
    0.46
     ምር
    0.45
     hypersurface
    0.45
    ك
    0.44
    nale
    0.44
    Ord
    0.43
     상품
    0.43
     అనుమ
    0.42
    Activations Density 0.000%

    No Known Activations