© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9781
    Prev
    Next
    INDEX
    Explanations

    code, programming, introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isez
    -1.27
    ₦
    -1.18
    ≅
    -1.13
    ndig
    -1.09
    ctober
    -1.08
    '],$
    -1.07
    ₱
    -1.07
    corrhi
    -1.05
    感を
    -1.02
    isit
    -1.02
    POSITIVE LOGITS
    Historio
    1.23
    <bos>
    1.17
    作り方
    1.13
    Eze
    1.09
    Mó
    1.09
    Modificar
    1.09
    Cré
    1.07
    Tó
    1.07
    Ár
    1.07
    Papier
    1.06
    Activations Density 0.000%

    No Known Activations