© 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. 10-GEMMASCOPE-RES-131K
    7. 68191
    Prev
    Next
    INDEX
    Explanations

    exists and findById

    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
     Warum
    -2.42
    m
    -2.41
     You
    -2.34
    and
    -2.27
    
    -2.25
    ("
    -2.14
     Siehe
    -2.13
    是用
    -2.09
    ising
    -2.08
    ̣i
    -2.05
    POSITIVE LOGITS
    .”
    2.63
     ‘
    2.53
    琁
    2.45
     However
    2.33
    anyahu
    2.30
     participado
    2.22
     tocado
    2.17
     Fällen
    2.17
     soeur
    2.17
     (‘
    2.13
    Activations Density 0.001%

    No Known Activations