© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4395
    Prev
    Next
    INDEX
    Explanations

    probability and fila

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Igbo
    1.38
    Cristiano
    1.18
     upwards
    1.11
     Iber
    1.06
     african
    1.05
     bitmap
    1.05
    史
    1.05
     Spart
    1.05
     الصف
    1.04
     Cristiano
    1.03
    POSITIVE LOGITS
     laboratorio
    0.93
     speriment
    0.89
    摺
    0.85
    lah
    0.84
     Vallée
    0.84
    ngl
    0.84
    eliti
    0.84
     Trudeau
    0.83
     Tink
    0.83
    oten
    0.82
    Activations Density 0.100%

    No Known Activations