© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12112
    Prev
    Next
    INDEX
    Explanations

    explanation preamble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underlying
    0.41
    :
    0.37
     equally
    0.36
     precursor
    0.35
     جوان
    0.35
     instructional
    0.35
     concept
    0.35
    Disclaimer
    0.35
    <strong>
    0.34
     Dont
    0.34
    POSITIVE LOGITS
    ных
    0.44
     alapján
    0.44
    $&$-
    0.42
    decyd
    0.42
     posisi
    0.41
    කින්
    0.41
    épaisseur
    0.41
    berts
    0.40
    हून
    0.40
     weinig
    0.40
    Activations Density 0.146%

    No Known Activations