© 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. 10-GEMMASCOPE-RES-131K
    7. 99508
    Prev
    Next
    INDEX
    Explanations

    chimeric

    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
    для
    -2.11
     използва
    -2.06
    栁
    -2.02
    ();
    -1.99
    也没
    -1.98
     изпол
    -1.97
     hvad
    -1.92
    ve
    -1.92
     tredje
    -1.92
     が
    -1.86
    POSITIVE LOGITS
    </b>
    3.00
     IBOutlet
    2.16
    ſſi
    2.08
    が良い
    1.99
    鲵
    1.93
    e
    1.91
    }
    1.90
    ⢓
    1.88
     dimin
    1.84
    </i>
    1.75
    Activations Density 0.004%

    No Known Activations