© 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. 74331
    Prev
    Next
    INDEX
    Explanations

    property, scenes, recognized by, justified as

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

    scam, bluff, rainbow blended

    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
    ಂಥ
    0.45
    6
    0.43
    砾
    0.42
     clade
    0.42
    2
    0.40
     mutta
    0.40
     ngunit
    0.40
    0
    0.40
     portée
    0.39
    9
    0.39
    POSITIVE LOGITS
     остав
    0.52
     приро
    0.51
     отказа
    0.48
     кризи
    0.48
     моего
    0.48
     प्रॉफिट
    0.48
     жела
    0.47
     мои
    0.47
     הע
    0.47
     наших
    0.47
    Activations Density 0.002%

    No Known Activations