© 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. 116049
    Prev
    Next
    INDEX
    Explanations

    related expenses, left me, also coming

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

    described colourful, watched you, about transmission

    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
    unding
    0.46
    íř
    0.45
    insi
    0.44
    uleiro
    0.44
    ená
    0.44
     方法
    0.44
     值
    0.43
    关于
    0.43
     lửa
    0.43
    .‏
    0.43
    POSITIVE LOGITS
     progen
    0.45
     sicht
    0.45
     uncertainty
    0.44
     overturned
    0.44
     materiality
    0.42
     altered
    0.42
     microcosm
    0.42
     spring
    0.42
     seizures
    0.42
     cess
    0.41
    Activations Density 0.000%

    No Known Activations