© 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. 204690
    Prev
    Next
    INDEX
    Explanations

    Golgi staining sections

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

    how to ask about processes

    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
    5
    0.53
    commands
    0.52
    1
    0.52
    Returns
    0.51
    9
    0.50
    cate
    0.48
    4
    0.46
     exhibiting
    0.46
    0
    0.46
    d
    0.46
    POSITIVE LOGITS
    Pda
    0.48
     Hau
    0.48
    зино
    0.47
     Bb
    0.46
    𝕘
    0.45
    скопа
    0.45
     سك
    0.44
    篷
    0.44
     Джо
    0.44
    зонта
    0.44
    Activations Density 0.000%

    No Known Activations