© 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. 3521
    Prev
    Next
    INDEX
    Explanations

    initiatives

    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
     Montevideo
    1.16
     ribs
    1.05
    윰
    1.05
     Stéph
    1.04
    ühlen
    1.03
     Thym
    1.01
     SDL
    1.01
    MUN
    1.00
     HCC
    0.99
     Mancini
    0.98
    POSITIVE LOGITS
     I
    1.43
    I
    1.43
    Again
    1.05
     It
    1.03
    It
    1.02
     So
    0.99
     A
    0.98
     Buy
    0.95
     Again
    0.95
     He
    0.94
    Activations Density 0.079%

    No Known Activations