© 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. 161826
    Prev
    Next
    INDEX
    Explanations

    for further context

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

    You can

    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
    wet
    0.55
    zw
    0.52
    '
    0.49
    áp
    0.49
    pet
    0.48
    :
    0.48
     үй
    0.47
    ay
    0.47
    uest
    0.47
    ban
    0.47
    POSITIVE LOGITS
    더
    0.52
     courte
    0.50
     Lula
    0.50
    𒆷
    0.50
    것도
    0.49
    시
    0.49
     capitalise
    0.48
     maliciously
    0.48
    드
    0.47
    𖤐
    0.47
    Activations Density 0.000%

    No Known Activations