© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130037
    Prev
    Next
    INDEX
    Explanations

    code array initializations

    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
     from
    -1.39
     and
    -1.26
     various
    -1.18
     to
    -1.17
     may
    -1.13
     any
    -1.12
     while
    -1.10
     appears
    -1.09
     might
    -1.06
    bilde
    -1.03
    POSITIVE LOGITS
     momente
    1.20
    '>"
    1.19
     []:
    1.15
    ᅠ
    1.14
     reforma
    1.12
     traduc
    1.08
     bambou
    1.07
     '/':
    1.07
     diminu
    1.06
     perak
    1.06
    Activations Density 0.011%

    No Known Activations