© 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. 191925
    Prev
    Next
    INDEX
    Explanations

    contrasting or comparing information

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

    film script

    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
    З
    0.49
    Ж
    0.49
     elementName
    0.47
    Ш
    0.46
     dirname
    0.46
     ere
    0.44
    К
    0.44
     for
    0.43
     modal
    0.42
     dz
    0.42
    POSITIVE LOGITS
    istice
    0.52
    悖
    0.52
     }//
    0.50
     அவர்களை
    0.50
    埶
    0.50
    ämp
    0.49
    ionato
    0.48
     طور
    0.48
     চালায়
    0.48
     سعی
    0.48
    Activations Density 0.000%

    No Known Activations