© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244968
    Prev
    Next
    INDEX
    Explanations

    career plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.57
    0.53
     al
    0.52
     Pasteur
    0.47
    1
    0.47
     Pey
    0.47
    </li>
    0.47
     absorption
    0.47
    8
    0.47
    6
    0.46
    POSITIVE LOGITS
    ்களை
    0.46
    빨
    0.46
    लब
    0.46
    माजिक
    0.46
    meni
    0.45
     काउंस
    0.45
    ்களின்
    0.45
    ippi
    0.44
    appliqu
    0.44
     আশে
    0.43
    Activations Density 0.000%

    No Known Activations