© 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. 92132
    Prev
    Next
    INDEX
    Explanations

    keywords for searching

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

    next ideas

    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
     yena
    0.52
    ल्लाला
    0.50
    Okno
    0.50
     volontà
    0.50
    Ḍ
    0.49
    jera
    0.48
    plementation
    0.47
     bertanggung
    0.47
     distraught
    0.47
     البلاد
    0.47
    POSITIVE LOGITS
    T
    0.53
    r
    0.45
     Aesthetics
    0.44
     पॉपुलर
    0.43
    ulf
    0.43
     Metrics
    0.41
    ell
    0.40
    m
    0.40
    计
    0.40
     génération
    0.40
    Activations Density 0.000%

    No Known Activations