© 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. 34296
    Prev
    Next
    INDEX
    Explanations

    Guest Post

    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
     ถูก
    -0.92
    Характеристики
    -0.87
     kecil
    -0.86
    ];
    -0.86
    𝒗
    -0.84
    ⍝
    -0.84
    ־
    -0.84
    ällning
    -0.84
     spezi
    -0.83
     posicion
    -0.83
    POSITIVE LOGITS
     note
    0.97
     rád
    0.90
     portátiles
    0.89
    (
    0.89
    첼
    0.85
     philosoph
    0.84
     Heist
    0.84
     يك
    0.83
     vacancy
    0.82
    ~
    0.82
    Activations Density 0.006%

    No Known Activations