© 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. 235078
    Prev
    Next
    INDEX
    Explanations

    saving your moneypersonalised gift

    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
    ق
    0.52
    "
    0.44
    ;\
    0.42
    ilah
    0.40
    ;<
    0.40
     দুপুর
    0.40
    विण्यात
    0.39
    _
    0.39
    Country
    0.38
     ambulances
    0.38
    POSITIVE LOGITS
     pełni
    0.56
     เล่น
    0.52
     बरस
    0.50
     ユニ
    0.50
     proporción
    0.50
    ěstí
    0.49
     モダン
    0.49
     ボ
    0.48
     учета
    0.48
     كرة
    0.48
    Activations Density 0.000%

    No Known Activations