© 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. 39069
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets with content

    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
     yetu
    -1.02
    enetrable
    -1.00
     ચ
    -0.91
    ̀n
    -0.91
    asarray
    -0.84
    拌
    -0.83
     democrática
    -0.83
    帖最后由
    -0.83
     conferma
    -0.82
    为你
    -0.82
    POSITIVE LOGITS
    “
    1.16
     (
    1.16
    ″]
    1.09
    “(
    1.05
    Places
    1.02
    dsa
    0.99
    ]
    0.99
    tawan
    0.97
    riva
    0.93
     Drittel
    0.91
    Activations Density 0.074%

    No Known Activations