© 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. 34-GEMMASCOPE-RES-131K
    7. 63791
    Prev
    Next
    INDEX
    Explanations

    things corresponding to each other

    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_34/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
    iesa
    -0.81
    NotBlank
    -0.79
    PAGER
    -0.76
     aceit
    -0.76
    Cách
    -0.75
    terung
    -0.74
     lucro
    -0.73
    أة
    -0.72
    ticularly
    -0.71
    yuk
    -0.71
    POSITIVE LOGITS
     corresponding
    7.03
     correspond
    6.25
     corresponds
    6.19
    corresponding
    6.16
    Corresponding
    5.78
     corresponded
    5.63
     Corresponding
    5.59
    对应
    5.47
     Correspond
    5.16
    correspond
    5.09
    Activations Density 0.315%

    No Known Activations