© 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. 75310
    Prev
    Next
    INDEX
    Explanations

    all but one

    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
     different
    -1.21
     treball
    -1.05
     verá
    -1.02
    lasyon
    -1.02
    <bos>
    -1.02
    Assemblée
    -1.00
     PUSTAKA
    -1.00
    ◪
    -0.98
    をよく
    -0.97
     différents
    -0.95
    POSITIVE LOGITS
     those
    1.38
    ۴
    1.23
    最后一个
    1.16
    اما
    1.14
     the
    1.13
    RemoteException
    1.05
     one
    1.05
    𝐟
    1.05
    '}';
    1.04
     néhány
    1.03
    Activations Density 0.016%

    No Known Activations