© 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. 241534
    Prev
    Next
    INDEX
    Explanations

    reporting details

    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
    Svg
    0.59
     climatique
    0.54
    INSON
    0.51
    Мы
    0.50
    IC
    0.50
     hommes
    0.49
    échange
    0.48
    <0x83>
    0.48
    ourt
    0.48
    ين
    0.48
    POSITIVE LOGITS
     scorching
    0.48
     アンティーク
    0.44
     winning
    0.44
     temporal
    0.43
     اید
    0.43
     प्रभा
    0.42
     حالی
    0.42
     sajana
    0.41
     מק
    0.41
    小屋
    0.41
    Activations Density 0.000%

    No Known Activations