© 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. 39196
    Prev
    Next
    INDEX
    Explanations

    who is, who spoke, unnamed, familiar

    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
    Seems
    -1.06
    sometimes
    -1.02
    ḕ
    -1.01
    Sometimes
    -1.00
     Nachbarn
    -0.95
    Actually
    -0.94
     gustar
    -0.94
    łeś
    -0.93
     Wohnungen
    -0.93
    Apparently
    -0.92
    POSITIVE LOGITS
     said
    1.30
    доба
    1.04
     before
    1.01
     during
    1.00
    的原因
    0.99
    不可思议
    0.98
     because
    0.94
     additionally
    0.92
     due
    0.90
    htë
    0.89
    Activations Density 0.002%

    No Known Activations