© 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. 208758
    Prev
    Next
    INDEX
    Explanations

    staged one, lovely big, any dangerous

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

    states and qualities

    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
     nont
    0.45
     ħ
    0.43
     veine
    0.42
     Optionen
    0.42
     chak
    0.41
     Objection
    0.41
     angios
    0.41
    나
    0.40
     lem
    0.40
     tani
    0.40
    POSITIVE LOGITS
    ക്ഷി
    0.49
    閲
    0.47
    триму
    0.47
     proyecto
    0.46
    욌
    0.46
     collectif
    0.46
     проект
    0.45
    axx
    0.44
    ｪ
    0.44
    ется
    0.44
    Activations Density 0.001%

    No Known Activations