© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65911
    Prev
    Next
    INDEX
    Explanations

    place and its area

    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
     to
    -1.50
    つまり
    -1.40
     (
    -1.25
    텝
    -1.16
     футболка
    -1.13
     potret
    -1.13
    )
    -1.13
    に関する
    -1.12
    Важно
    -1.10
    她就
    -1.09
    POSITIVE LOGITS
     space
    1.45
     gebou
    1.44
     auriculares
    1.34
     and
    1.33
    煒
    1.32
     gemeenten
    1.30
     place
    1.29
     tallas
    1.27
     centre
    1.27
     center
    1.26
    Activations Density 0.131%

    No Known Activations