© 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. 134376
    Prev
    Next
    INDEX
    Explanations

    noun followed by related word

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

    actions followed by prepositions/objects

    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
    掝
    0.49
     بہانہ
    0.48
    ೖ
    0.48
    iczne
    0.47
    itä
    0.47
    ത്തിന്റെയും
    0.46
     جانے
    0.46
    ongiorno
    0.46
    textepsilon
    0.46
     riduzione
    0.45
    POSITIVE LOGITS
    新
    0.51
    ס
    0.49
     cra
    0.47
    ق
    0.46
    ਰ
    0.45
    ਚ
    0.45
    ppers
    0.45
    Sem
    0.44
     Sem
    0.44
     af
    0.43
    Activations Density 0.001%

    No Known Activations