© 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. 34-GEMMASCOPE-RES-131K
    7. 78207
    Prev
    Next
    INDEX
    Explanations

    I followed by verb

    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_34/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
     and
    -1.30
     from
    -1.16
     on
    -1.05
    lorin
    -1.00
     Mark
    -1.00
     White
    -0.95
     Unique
    -0.95
     Green
    -0.94
     Joe
    -0.94
     as
    -0.92
    POSITIVE LOGITS
     recently
    1.20
     otak
    1.16
     purchased
    1.14
     mentioned
    1.11
     always
    1.08
     adoro
    1.08
     peman
    1.08
     morena
    1.02
     realized
    1.00
     fotografi
    0.99
    Activations Density 0.075%

    No Known Activations