© 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. 61797
    Prev
    Next
    INDEX
    Explanations

    dissolved in

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

    avoid C

    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
     leer
    0.45
    نت
    0.43
    خ
    0.43
    ش
    0.42
    \
    0.41
    ث
    0.40
    τε
    0.38
    ﺛ
    0.38
     maintien
    0.38
    ivent
    0.37
    POSITIVE LOGITS
     உலகில்
    0.55
    dSample
    0.52
    atthaya
    0.50
    躹
    0.50
     cryptography
    0.49
    ಗ್ಗೆ
    0.49
     যুগে
    0.48
     നല്ല
    0.48
     সৈ
    0.47
     ഭക്ഷണം
    0.47
    Activations Density 0.000%

    No Known Activations