© 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. 117272
    Prev
    Next
    INDEX
    Explanations

    goes further or back

    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
     go
    -1.37
     going
    -1.26
     goin
    -1.09
    ไป
    -1.04
     gaan
    -1.00
    去
    -0.98
     went
    -0.95
     Going
    -0.94
    gå
    -0.94
    GOING
    -0.92
    POSITIVE LOGITS
     alongside
    1.33
     against
    1.32
     along
    1.27
     beyond
    1.24
     hand
    1.23
     unnoticed
    1.16
    Hand
    1.05
     by
    1.05
     together
    1.04
     something
    0.95
    Activations Density 0.016%

    No Known Activations