© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71121
    Prev
    Next
    INDEX
    Explanations

    plain text or geometric plane

    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
     téměř
    -2.45
    }
    -2.45
     awe
    -2.31
     ‘‘
    -2.23
     Gedanke
    -2.20
     (‘
    -2.13
     gestern
    -2.13
    獃
    -2.11
    商场
    -2.08
     хранения
    -2.06
    POSITIVE LOGITS
    ֟
    2.64
    ╽
    2.63
     faſt
    2.41
     uſed
    2.41
     kuning
    2.36
     grupp
    2.34
    媜
    2.31
     wohnung
    2.28
     lebte
    2.28
    你也
    2.23
    Activations Density 0.009%

    No Known Activations