© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66738
    Prev
    Next
    INDEX
    Explanations

    Paranoid album song

    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
    ͹
    -1.13
     atau
    -1.01
    reszcie
    -0.98
    tuje
    -0.97
     registrado
    -0.96
    躄
    -0.96
    windig
    -0.96
    tissimo
    -0.95
     ingrediente
    -0.93
     leopardo
    -0.91
    POSITIVE LOGITS
    Their
    0.90
    Ź
    0.90
     Incluye
    0.84
     lea
    0.83
     einerseits
    0.83
     part
    0.81
    lea
    0.80
     ①
    0.79
     Sólo
    0.79
    大な
    0.78
    Activations Density 0.127%

    No Known Activations