© 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. 242501
    Prev
    Next
    INDEX
    Explanations

    exam questions

    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
     disease
    0.44
     pharmac
    0.43
     name
    0.43
     causative
    0.42
    SI
    0.42
    ac
    0.41
    hydro
    0.41
    .
    0.41
     amphibians
    0.40
    they
    0.39
    POSITIVE LOGITS
     Anushka
    0.48
     Jinping
    0.48
    饗
    0.48
     Deepika
    0.48
     Meghan
    0.47
    xcuser
    0.46
     Rihanna
    0.46
    ︽
    0.46
    বারের
    0.46
     ফিরিয়ে
    0.45
    Activations Density 0.001%

    No Known Activations