© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67444
    Prev
    Next
    INDEX
    Explanations

    Java imports and classes

    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
     vence
    -1.52
     ilumina
    -1.48
     retira
    -1.45
     our
    -1.45
    珦
    -1.44
     espel
    -1.40
    endpush
    -1.39
    ſelf
    -1.38
    𖤣
    -1.38
    iedenen
    -1.38
    POSITIVE LOGITS
    <bos>
    2.05
    3
    1.63
    2
    1.58
    4
    1.57
    1
    1.54
    0
    1.48
    5
    1.38
    を
    1.37
    <0xA3>
    1.36
    6
    1.35
    Activations Density 0.001%

    No Known Activations