© 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. 31697
    Prev
    Next
    INDEX
    Explanations

    grading of evidence

    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
     refused
    -0.82
    曄
    -0.79
    祈祷
    -0.77
    ANOVA
    -0.74
     poner
    -0.73
     Milner
    -0.73
    Далее
    -0.71
     Stru
    -0.71
    髑
    -0.71
    vai
    -0.70
    POSITIVE LOGITS
     evidence
    2.08
     GRADE
    1.63
    Evidence
    1.59
    evidence
    1.58
     level
    1.48
     Evidence
    1.45
    证据
    1.41
    Strong
    1.37
    Level
    1.33
     strongest
    1.32
    Activations Density 0.141%

    No Known Activations