© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127971
    Prev
    Next
    INDEX
    Explanations

    finding something somewhere

    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_10/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
    .
    -1.25
    baka
    -1.25
    commodation
    -1.23
    躄
    -1.23
     verhind
    -1.23
    experience
    -1.23
     razie
    -1.22
    Bains
    -1.22
     srebr
    -1.21
    Nếu
    -1.20
    POSITIVE LOGITS
     then
    1.62
     also
    1.54
    ma
    1.38
    </tbody>
    1.33
    ss
    1.31
    "></
    1.29
     their
    1.28
     but
    1.28
     more
    1.27
    ust
    1.24
    Activations Density 0.072%

    No Known Activations