© 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-16K
    7. 841
    Prev
    Next
    INDEX
    Explanations

    data and code structure

    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_16k_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
    wa
    1.24
    wand
    1.19
    w
    1.14
    ウォ
    1.08
    hew
    1.07
     ウォ
    1.05
    wi
    1.04
    W
    1.03
     W
    1.00
    WA
    0.99
    POSITIVE LOGITS
     Jays
    0.87
     Jas
    0.86
     cps
    0.84
     generative
    0.83
     Jann
    0.82
     Supervisors
    0.82
    Jas
    0.82
     niss
    0.81
     Gener
    0.80
    supervisor
    0.80
    Activations Density 0.373%

    No Known Activations