© 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. 67158
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation

    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
    踯
    -2.09
    ᠂
    -1.92
    萏
    -1.70
    曾在
    -1.69
    }}
    -1.58
    er
    -1.55
     ロング
    -1.51
    硨
    -1.48
    勫
    -1.45
    <em>
    -1.44
    POSITIVE LOGITS
     Ironically
    1.66
    媄
    1.63
    Scrub
    1.59
    PRIVACY
    1.59
    yskland
    1.59
    烔
    1.59
     Interestingly
    1.54
     also
    1.54
     Bewußt
    1.53
     Jerusalén
    1.51
    Activations Density 0.013%

    No Known Activations