© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73394
    Prev
    Next
    INDEX
    Explanations

    good followed by positive descriptor

    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_10/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
    -2.33
     neun
    -2.06
     a
    -2.05
    饧
    -1.93
    ⍢
    -1.92
    皛
    -1.91
    䊐
    -1.91
     quintessential
    -1.91
    烀
    -1.84
     magnificent
    -1.83
    POSITIVE LOGITS
    先日
    1.68
     enough
    1.67
    ());
    1.66
    。”
    1.62
    ”,
    1.60
     Puerta
    1.59
    vimos
    1.59
    .”
    1.59
    };
    1.57
    ):
    1.54
    Activations Density 0.025%

    No Known Activations