© 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. 128314
    Prev
    Next
    INDEX
    Explanations

    Primary links, EFF leader

    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
     Direito
    -1.38
    endforeach
    -1.34
    bibinfo
    -1.33
     from
    -1.33
     Mesin
    -1.30
    ctober
    -1.29
    signee
    -1.27
    onyme
    -1.27
     Informações
    -1.27
     sés
    -1.26
    POSITIVE LOGITS
    _
    1.53
    le
    1.47
    3
    1.37
    <bos>
    1.35
    ka
    1.32
    )
    1.30
    des
    1.26
    ha
    1.25
    an
    1.25
    ↵
    1.24
    Activations Density 0.000%

    No Known Activations