© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    learning about something specific

    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
    timmung
    -0.89
     often
    -0.88
     observed
    -0.88
    scsi
    -0.85
     sometimes
    -0.82
    enscha
    -0.81
     マット
    -0.79
    ädigung
    -0.79
    /−
    -0.78
    كذا
    -0.78
    POSITIVE LOGITS
     of
    3.45
     about
    1.84
     của
    1.05
    ของ
    1.04
    назна
    1.02
    of
    1.01
     details
    1.01
    приєм
    0.94
     learns
    0.94
     from
    0.93
    Activations Density 0.023%

    No Known Activations