© 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. 69355
    Prev
    Next
    INDEX
    Explanations

    right to, Board provided, antioxidants and, unless I, ale ., cross to

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

    existing plays, food temperature, cat peeking

    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
     ரொ
    0.50
    icin
    0.47
    łki
    0.47
    alary
    0.46
     plata
    0.45
    硞
    0.45
    isesti
    0.44
    oglobine
    0.43
    Oste
    0.43
    î
    0.43
    POSITIVE LOGITS
     stakeholder
    0.47
     philanthropic
    0.46
     چاہی
    0.45
     songwriter
    0.45
     confectionery
    0.45
     artístico
    0.45
     nonprofit
    0.44
     statutory
    0.44
     brainchild
    0.44
     patented
    0.43
    Activations Density 0.001%

    No Known Activations