© 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. 219617
    Prev
    Next
    INDEX
    Explanations

    special request wait obtenir

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

    fantasy adventure genres

    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
    of
    0.55
    쿄
    0.50
    ΙΑ
    0.49
    2
    0.48
    AEA
    0.47
    ónica
    0.46
    _
    0.46
    도
    0.46
    ographed
    0.45
    4
    0.45
    POSITIVE LOGITS
     warten
    0.51
     obtenir
    0.50
     Unterstüt
    0.50
     speciale
    0.50
     chiedere
    0.49
     spezielle
    0.49
     attendre
    0.48
     inget
    0.47
     træ
    0.47
     aște
    0.47
    Activations Density 0.000%

    No Known Activations