© 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. 63074
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and life experiences

    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
    bietet
    -1.17
    Mostrar
    -1.16
    HANG
    -1.14
    rufen
    -1.08
     tarafından
    -1.08
    çoise
    -1.07
    könyv
    -1.06
     œuvre
    -1.05
     byli
    -1.04
    bleiben
    -1.04
    POSITIVE LOGITS
     is
    3.22
     can
    2.22
     always
    2.08
     comes
    2.03
     isn
    2.00
     doesn
    1.98
     shouldn
    1.97
     cannot
    1.72
     wasn
    1.61
     should
    1.59
    Activations Density 0.097%

    No Known Activations