© 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. 62010
    Prev
    Next
    INDEX
    Explanations

    biological assays

    np_acts-logits-general · gemini-2.5-flash-lite

    cells, organs, volume, length

    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
    蟆
    0.48
    Rain
    0.47
    йын
    0.46
    Sliced
    0.44
     решили
    0.44
     ovviamente
    0.44
     semplic
    0.44
    Nazi
    0.44
     شي
    0.43
     création
    0.43
    POSITIVE LOGITS
     assays
    0.49
     bodies
    0.46
     arenas
    0.44
     *)&
    0.43
     cells
    0.43
     increments
    0.42
     pallets
    0.42
     compounds
    0.42
     predictors
    0.42
     swabs
    0.42
    Activations Density 0.000%

    No Known Activations