© 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. 63826
    Prev
    Next
    INDEX
    Explanations

    effect of

    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
     anarch
    -1.24
    ⩥
    -1.09
     exceptionally
    -1.06
    
    -1.02
    先是
    -1.02
    います
    -1.02
     insanely
    -1.00
    iest
    -1.00
     esist
    -0.98
    AN
    -0.98
    POSITIVE LOGITS
     on
    1.68
     Effects
    1.38
     Effect
    1.36
     exerted
    1.16
    Effect
    1.16
     französische
    1.12
     ottenuto
    1.12
     effects
    1.11
     effect
    1.09
     of
    1.08
    Activations Density 0.071%

    No Known Activations