© 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. 22-GEMMASCOPE-RES-131K
    7. 73292
    Prev
    Next
    INDEX
    Explanations

    ; . ) }

    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_22/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
    -0.89
    了一個
    -0.88
     to
    -0.86
    личный
    -0.84
    ールの
    -0.83
    一旁的
    -0.82
     by
    -0.82
     Run
    -0.82
     league
    -0.81
     OR
    -0.81
    POSITIVE LOGITS
     beide
    1.17
     begge
    1.01
     KONG
    1.00
    ⃰
    0.95
    HPLC
    0.89
     båda
    0.89
     siège
    0.88
    cuando
    0.87
    volumen
    0.86
     Cian
    0.85
    Activations Density 0.008%

    No Known Activations