© 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. 34-GEMMASCOPE-RES-131K
    7. 32655
    Prev
    Next
    INDEX
    Explanations

    identifying criteria for

    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
     Maintaining
    -1.05
     émission
    -1.03
     uncovering
    -1.02
     Vertrauen
    -1.01
     Utilizing
    -1.00
     icône
    -1.00
    parian
    -0.99
     Gives
    -0.96
    紅色
    -0.96
    målet
    -0.96
    POSITIVE LOGITS
     for
    1.34
     criteria
    1.31
     Criteria
    1.21
     criterion
    1.18
    Criteria
    1.16
    criterion
    1.16
     crit
    1.16
     Crit
    1.16
    Crit
    1.15
    riteria
    1.09
    Activations Density 0.012%

    No Known Activations