© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1381
    Prev
    Next
    INDEX
    Explanations

    require or import statements

    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_34/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
     bym
    -1.04
     zrobić
    -1.02
     (
    -1.02
    )
    -1.00
    (
    -1.00
     said
    -0.99
     hivyo
    -0.96
     veckan
    -0.92
    timus
    -0.90
    せば
    -0.89
    POSITIVE LOGITS
     './
    1.84
     "./
    1.66
     "";
    1.23
     };
    1.14
     ਵਿੱਚ
    1.13
    ("./
    1.11
    lblNewLabel
    1.09
    חן
    1.08
    توضیحات
    1.08
    なども
    1.07
    Activations Density 0.010%

    No Known Activations