© 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. 198104
    Prev
    Next
    INDEX
    Explanations

    medicine, dosage, cases

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

    RDP, SSH, project management

    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
    ដំណើរ
    0.53
    raz
    0.46
    :
    0.44
     জীব
    0.44
    圆
    0.43
     formulating
    0.43
    ableness
    0.43
     घे
    0.42
     انصاف
    0.42
    พระ
    0.42
    POSITIVE LOGITS
     shielded
    0.48
     bode
    0.47
     Tehran
    0.46
     Uzbek
    0.45
     Kamil
    0.45
     Andrade
    0.44
     Erde
    0.44
    KAM
    0.44
    叒
    0.44
     患者
    0.44
    Activations Density 0.000%

    No Known Activations