© 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. 4753
    Prev
    Next
    INDEX
    Explanations

    how to ask

    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
    Basic
    1.16
    3
    1.10
     basic
    1.09
    basic
    1.08
     básicos
    1.02
     Basic
    1.02
    licensed
    0.98
    5
    0.97
     Juniper
    0.97
     базо
    0.95
    POSITIVE LOGITS
     how
    2.88
    how
    2.62
    How
    2.48
     How
    2.48
     cómo
    2.21
     HOW
    2.16
    cómo
    2.04
    如何
    2.03
     Cómo
    1.99
     hoe
    1.95
    Activations Density 0.137%

    No Known Activations