© 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. 209003
    Prev
    Next
    INDEX
    Explanations

    numbers followed by titles

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

    RDP, Pareto Principle, niche

    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
     كل
    0.51
     carcinoma
    0.50
     لڑ
    0.49
     рыба
    0.48
     w
    0.48
     زیاد
    0.47
     Kel
    0.47
     wart
    0.47
     ذکر
    0.47
    隗
    0.46
    POSITIVE LOGITS
    sächlich
    0.43
    gger
    0.41
    Autoresizing
    0.40
    ̀u
    0.40
    ĵo
    0.39
    ʼn
    0.39
     HUB
    0.39
    ουν
    0.39
    ública
    0.38
    ldquo
    0.38
    Activations Density 0.000%

    No Known Activations