© 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. 3595
    Prev
    Next
    INDEX
    Explanations

    code and examples

    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
    8
    1.21
    7
    1.16
    0
    1.12
    6
    1.11
    4
    1.07
    9
    1.05
    5
    0.98
    DHT
    0.91
    3
    0.84
    HIDE
    0.82
    POSITIVE LOGITS
     soci
    1.06
     carbohydrate
    1.00
    맬
    1.00
     orthodont
    0.99
    rosse
    0.98
     Scarlett
    0.96
     polysaccharide
    0.96
    okine
    0.96
    port
    0.95
    RECTION
    0.93
    Activations Density 0.037%

    No Known Activations