© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16347
    Prev
    Next
    INDEX
    Explanations

    specific followed by context

    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
    sandalia
    -0.89
     która
    -0.87
    Música
    -0.86
    Christine
    -0.86
     microfibra
    -0.83
    Reis
    -0.83
     Kühlschrank
    -0.83
    Exceeded
    -0.82
    Hutch
    -0.82
    成功
    -0.82
    POSITIVE LOGITS
    </b>
    1.60
    </strong>
    1.54
    </i>
    1.17
    </em>
    1.13
    </code>
    1.05
    </u>
    0.91
    ally
    0.91
    ump
    0.83
    )
    0.79
    透过
    0.79
    Activations Density 0.009%

    No Known Activations