© 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. 60839
    Prev
    Next
    INDEX
    Explanations

    form or dps

    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
    当即
    -1.18
     investissements
    -1.13
    ?\
    -1.09
    mäßigen
    -1.06
     propriétaires
    -1.06
     verschillende
    -1.06
     inextrica
    -1.06
    pullover
    -1.05
     bangun
    -1.05
    mucho
    -1.03
    POSITIVE LOGITS
     why
    1.35
     reasons
    1.28
    If
    1.21
     required
    1.18
    Here
    1.13
     difficulties
    1.12
     reason
    1.10
    ordenadas
    1.10
    igarette
    1.08
    ل
    1.08
    Activations Density 0.086%

    No Known Activations