© 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. 74416
    Prev
    Next
    INDEX
    Explanations

    descriptive noun phrases

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

    allocating space or making a wager

    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
    ಾವ
    0.49
     vitesses
    0.47
    𝐭
    0.47
     ennemis
    0.47
     renforc
    0.46
     vadati
    0.46
     relatifs
    0.46
    𝘁
    0.46
     pręd
    0.46
     tâ
    0.45
    POSITIVE LOGITS
    the
    0.51
    ra
    0.51
    wen
    0.50
    len
    0.49
    esy
    0.49
     originality
    0.49
    ova
    0.48
    sey
    0.47
    原始
    0.47
     vitality
    0.47
    Activations Density 0.000%

    No Known Activations