© 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. 22-GEMMASCOPE-RES-131K
    7. 26605
    Prev
    Next
    INDEX
    Explanations

    connects clauses

    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
     a
    -1.38
     Eigentum
    -0.92
    钥
    -0.89
     an
    -0.88
    Lizard
    -0.87
    の話
    -0.86
    涉及
    -0.84
    سى
    -0.84
     dunia
    -0.84
     something
    -0.84
    POSITIVE LOGITS
     especially
    1.41
     feel
    1.40
     especialmente
    1.16
     ESPEC
    1.15
     appreciate
    1.13
     soprattutto
    1.10
     možnost
    1.09
    őle
    1.08
     ability
    1.06
     know
    1.05
    Activations Density 0.039%

    No Known Activations