© 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. 34-GEMMASCOPE-RES-131K
    7. 81435
    Prev
    Next
    INDEX
    Explanations

    describes states of being

    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_34/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
    sition
    -1.16
    stående
    -1.11
    schuhe
    -1.09
    ských
    -1.06
    😱
    -1.03
    Positioned
    -1.02
    ❔
    -1.00
    (/^
    -0.98
    <td>
    -0.98
    🧐
    -0.98
    POSITIVE LOGITS
     reflected
    1.90
     what
    1.76
     further
    1.66
     evident
    1.64
     also
    1.60
     part
    1.60
     shared
    1.59
     present
    1.52
     something
    1.48
     apparent
    1.46
    Activations Density 0.075%

    No Known Activations