© 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. 10-GEMMASCOPE-RES-131K
    7. 20810
    Prev
    Next
    INDEX
    Explanations

    questions starting with "have you"

    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_10/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
     was
    -2.13
    because
    -2.08
     required
    -2.06
     caído
    -2.03
    tabria
    -2.02
     军
    -1.95
    anggap
    -1.92
     孩子
    -1.88
     responsibly
    -1.88
    ]
    -1.86
    POSITIVE LOGITS
     been
    4.03
    蓠
    2.84
     accuses
    2.58
    endforeach
    2.38
    ps
    2.27
     ་
    2.23
     myriad
    2.23
    м
    2.22
     "
    2.20
    providedIn
    2.20
    Activations Density 0.004%

    No Known Activations