© 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. 183813
    Prev
    Next
    INDEX
    Explanations

    charged, continues, follow, risks, hands, for, cab, the national, contractor, Hampton

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

    image generation and automatic reasoning

    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
     표시
    0.47
     純
    0.46
     proletariat
    0.45
    ot
    0.45
     聞い
    0.45
     چنین
    0.44
    ウム
    0.44
    rée
    0.44
     Helv
    0.43
    thisobject
    0.43
    POSITIVE LOGITS
    વ
    0.48
     oxi
    0.48
     familiare
    0.46
     weights
    0.46
     rutas
    0.46
     frictions
    0.45
     lf
    0.45
    Мне
    0.45
     fracciones
    0.44
    मैंने
    0.43
    Activations Density 0.001%

    No Known Activations