© 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. 10-GEMMASCOPE-RES-131K
    7. 14361
    Prev
    Next
    INDEX
    Explanations

    parameter values

    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
    铎
    -1.35
    niť
    -1.31
    psfrag
    -1.20
    المل
    -1.16
    ed
    -1.15
    ꯠ
    -1.14
     because
    -1.12
    тельностью
    -1.11
    ées
    -1.09
    jącym
    -1.08
    POSITIVE LOGITS
     here
    1.34
     mencionar
    1.27
    ₁,
    1.20
     alfab
    1.14
     эксперимента
    1.11
     Thessal
    1.10
    ‪.
    1.09
    …
    1.09
    いずれ
    1.06
     Chunk
    1.06
    Activations Density 0.044%

    No Known Activations