© 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. 22-GEMMASCOPE-RES-131K
    4. 129445
    Prev
    Next
    INDEX
    Explanations

    IBM points, List of, was a

    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
     various
    -1.34
     to
    -1.27
     both
    -1.21
     some
    -1.20
     each
    -1.09
     different
    -1.03
     exuberant
    -1.02
     overtly
    -0.98
    男の子
    -0.98
     several
    -0.97
    POSITIVE LOGITS
     is
    1.06
    之为
    1.04
    )$,
    1.02
     哪些
    1.02
    }=\
    0.99
     maxime
    0.98
    })=\
    0.97
    }$,
    0.97
    }(\
    0.97
     fides
    0.96
    Activations Density 0.000%

    No Known Activations