© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12926
    Prev
    Next
    INDEX
    Explanations

    possibilities and expectations

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

    you might want

    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_16k_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
    of
    0.47
    ขาว
    0.43
    jLabel
    0.43
    the
    0.42
     mapping
    0.41
    Of
    0.41
    ta
    0.40
    t
    0.40
    frac
    0.39
     magnified
    0.39
    POSITIVE LOGITS
     کھیلو
    0.43
     গৃহে
    0.42
     investimento
    0.41
     capacités
    0.41
     jakie
    0.40
    льнай
    0.40
    स्तेमाल
    0.40
    ᾶ
    0.40
     publicités
    0.40
     zufrieden
    0.40
    Activations Density 0.004%

    No Known Activations