© 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. 10-GEMMASCOPE-RES-131K
    7. 71519
    Prev
    Next
    INDEX
    Explanations

    descriptive prefixes

    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
     on
    -1.73
     –
    -1.72
    v
    -1.53
     (“
    -1.49
    }
    -1.48
     having
    -1.47
    b
    -1.47
     “
    -1.46
     two
    -1.43
    ].
    -1.43
    POSITIVE LOGITS
    //!
    1.80
     différentes
    1.75
    媄
    1.73
     estrena
    1.73
    ऩ
    1.62
     différents
    1.59
     verschillende
    1.59
    鍆
    1.58
    utsches
    1.55
     ส์
    1.55
    Activations Density 0.041%

    No Known Activations