© 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. 225465
    Prev
    Next
    INDEX
    Explanations

    on the next word

    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
    從
    0.49
    ini
    0.45
     operation
    0.45
    deficient
    0.45
    niveau
    0.44
     Disabled
    0.44
    雖然
    0.44
     Decree
    0.44
    ิ
    0.44
     Deficiency
    0.43
    POSITIVE LOGITS
     সেসব
    0.48
    ."
    0.47
     Жу
    0.46
     геро
    0.46
     cánh
    0.46
     весьма
    0.45
     Kear
    0.45
     पुस्तकें
    0.44
    대의
    0.44
    <unused486>
    0.44
    Activations Density 0.001%

    No Known Activations