© 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. 10-GEMMASCOPE-RES-131K
    7. 100960
    Prev
    Next
    INDEX
    Explanations

    foray into, incurs, inroads

    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
    俢
    -2.39
     BRASIL
    -2.27
     climático
    -2.27
     MUNDO
    -2.25
    祧
    -2.22
    C
    -2.16
    纒
    -2.13
    𓆜
    -2.11
     fhould
    -2.08
    </td>
    -2.06
    POSITIVE LOGITS
     foray
    2.64
     renowned
    2.44
     ‘
    2.39
     majestic
    2.27
     …..
    2.27
    …….
    2.25
     mevcut
    2.23
     !!!!
    2.23
     enigmatic
    2.20
     ravaged
    2.19
    Activations Density 0.003%

    No Known Activations