© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72188
    Prev
    Next
    INDEX
    Explanations

    compressive strength and deformation

    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
    Negative Logits
     说
    -2.59
     الفترة
    -2.42
    ของ
    -2.41
    }=\
    -2.33
    leq
    -2.28
    rightarrow
    -2.28
    cinogenicity
    -2.28
     }{\
    -2.28
    XXI
    -2.25
    锺
    -2.23
    POSITIVE LOGITS
     esmeralda
    3.19
     “
    2.91
    。“
    2.86
    “,
    2.64
     portatil
    2.59
     possesses
    2.59
    is
    2.59
     precludes
    2.41
     categor
    2.39
     accompanying
    2.39
    Activations Density 0.006%

    No Known Activations