© 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. 128970
    Prev
    Next
    INDEX
    Explanations

    Product details

    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
    などを
    -1.28
    かもしれませんが
    -1.24
    があり
    -1.20
     Tampoco
    -1.15
     gefe
    -1.14
    が
    -1.13
    okkal
    -1.13
    pholes
    -1.12
     compositeur
    -1.10
    肴
    -1.10
    POSITIVE LOGITS
     bArr
    1.23
    </tbody>
    1.20
    為に
    1.19
    Begriffsklä
    1.19
     macetas
    1.16
    itrile
    1.16
    なんですよ
    1.14
    たびに
    1.13
    IBILITIES
    1.13
     or
    1.13
    Activations Density 0.012%

    No Known Activations