© 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. 135148
    Prev
    Next
    INDEX
    Explanations

    property and liability

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

    Friedrich Nietzsche translations

    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
    t
    0.57
    q
    0.57
    d
    0.57
    is
    0.56
    se
    0.52
    к
    0.52
    HCO
    0.52
    á
    0.50
    bra
    0.50
    é
    0.50
    POSITIVE LOGITS
     Friedrich
    0.49
     propriété
    0.48
    ွင်း
    0.47
     öpp
    0.45
     thấy
    0.44
    љено
    0.44
     verfügbar
    0.43
     आगमन
    0.43
     glad
    0.43
     habido
    0.43
    Activations Density 0.000%

    No Known Activations