© 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. 12528
    Prev
    Next
    INDEX
    Explanations

    API endpoints and REST concepts

    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
     each
    -1.26
     hjemmes
    -1.17
     stør
    -1.16
     illustrationer
    -1.16
     manufactures
    -1.11
    '
    -1.09
    PS
    -1.07
     valgt
    -1.06
     from
    -1.05
    natured
    -1.05
    POSITIVE LOGITS
    บริการ
    1.27
    האם
    1.25
    Nasc
    1.25
    brauch
    1.24
    שלום
    1.20
    危機
    1.16
     autorisation
    1.14
    嗚
    1.13
    Мир
    1.13
    Beijos
    1.13
    Activations Density 0.001%

    No Known Activations