© 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. 22-GEMMASCOPE-RES-131K
    7. 66995
    Prev
    Next
    INDEX
    Explanations

    young people

    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_22/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
     gracioso
    -1.22
     a
    -1.20
     sumamente
    -1.13
     humankind
    -1.13
     régle
    -1.09
     delicado
    -1.09
     entière
    -1.08
    をします
    -1.05
     équipée
    -1.05
     chaude
    -1.05
    POSITIVE LOGITS
     of
    1.37
     in
    1.30
     (<
    1.27
    QUET
    1.19
     этого
    1.17
    lexia
    1.14
    この
    1.11
    その
    1.09
    anasia
    1.08
    勇者
    1.05
    Activations Density 0.019%

    No Known Activations