© 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. 27081
    Prev
    Next
    INDEX
    Explanations

    museums, libraries, and collections

    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
    ૉ
    -1.38
    âts
    -1.20
    }$,
    -1.16
    整整
    -1.13
    につき
    -1.13
     July
    -1.11
    覗
    -1.11
     was
    -1.11
    }\}$
    -1.09
     waarmee
    -1.09
    POSITIVE LOGITS
    Історія
    1.28
     зберіга
    1.21
    adır
    1.20
    dekat
    1.16
     ricette
    1.13
     sfera
    1.13
    摆手
    1.13
     religieux
    1.12
     escolas
    1.10
    ᵏ
    1.09
    Activations Density 0.030%

    No Known Activations