© 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. 157318
    Prev
    Next
    INDEX
    Explanations

    figure theory limitations vis Attribute Table page SEO malpractice

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

    clear statements and hooks

    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
     Randomized
    0.49
     versucht
    0.48
    Bacteria
    0.46
    )(=
    0.45
     ब्यूरो
    0.45
    一部分
    0.45
    EXCLUSIVE
    0.45
    Greg
    0.44
     randomized
    0.44
    一
    0.43
    POSITIVE LOGITS
    ad
    0.50
     conten
    0.49
     duplicate
    0.46
     inic
    0.46
    instit
    0.46
    sub
    0.46
     teş
    0.45
    cin
    0.45
    loride
    0.45
     kinerja
    0.45
    Activations Density 0.001%

    No Known Activations