© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68475
    Prev
    Next
    INDEX
    Explanations

    center of or for

    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
    𓁹
    -2.70
     overarching
    -2.61
    栒
    -2.45
     breadth
    -2.44
     dando
    -2.34
     startling
    -2.33
    Y
    -2.33
     exceptional
    -2.31
     spectacular
    -2.28
     remarkably
    -2.28
    POSITIVE LOGITS
    With
    2.92
    ଞ
    2.86
    𖥦
    2.73
    on
    2.55
    with
    2.53
    Maybe
    2.48
    🌟
    2.45
    ">
    2.39
    });
    2.36
    𓍯
    2.36
    Activations Density 0.032%

    No Known Activations