© 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. 130109
    Prev
    Next
    INDEX
    Explanations

    starts and ends

    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
    洐
    -2.30
    coment
    -2.14
     münchen
    -2.13
     gewicht
    -2.11
     OXFORD
    -2.09
    ългар
    -2.08
    capped
    -2.02
     consisting
    -2.00
     ſta
    -2.00
     FRES
    -1.99
    POSITIVE LOGITS
    es
    2.58
     like
    2.25
     When
    2.19
     After
    2.02
    of
    2.00
     '
    1.98
     wants
    1.95
     gets
    1.94
     Even
    1.93
     Each
    1.93
    Activations Density 0.377%

    No Known Activations