© 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. 143639
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    listing features and actions

    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
    recently
    0.48
    although
    0.46
     खासा
    0.46
    orette
    0.42
    pubescens
    0.41
    othelium
    0.41
    ленд
    0.41
    }.$
    0.41
    arch
    0.41
    yrıca
    0.41
    POSITIVE LOGITS
     sulle
    0.44
     opérations
    0.44
     gên
    0.44
     înviat
    0.43
     关于
    0.43
    ികിത്സ
    0.43
    围绕
    0.42
     قیام
    0.42
     symbolName
    0.42
     superClass
    0.41
    Activations Density 0.002%

    No Known Activations