© 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. 55306
    Prev
    Next
    INDEX
    Explanations

    ATM machine

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

    list markers or separators

    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
     Awakening
    0.52
     awaken
    0.51
     Pé
    0.47
    ன்னை
    0.46
     Olympi
    0.46
    ☘
    0.46
     ObjData
    0.45
     Aerospace
    0.45
     Estadística
    0.44
     Comité
    0.44
    POSITIVE LOGITS
    ദന
    0.56
    elabor
    0.53
    zelfde
    0.49
     работа
    0.47
    ﻟ
    0.46
    之旅
    0.45
    不僅
    0.45
     agent
    0.44
     giusta
    0.42
    equilibrium
    0.42
    Activations Density 0.000%

    No Known Activations