© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103982
    Prev
    Next
    INDEX
    Explanations

    bookmark the permalink

    np_acts-logits-general · gemini-2.5-flash-lite

    doctors are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    д
    0.52
     alfabeto
    0.51
     counteract
    0.50
    čnom
    0.49
     columnIndex
    0.48
    ಿಣ
    0.46
     случа
    0.46
     sonore
    0.46
     ಕಂಪ
    0.45
     вид
    0.45
    POSITIVE LOGITS
    都
    0.49
    이랑
    0.46
    s
    0.45
    地元
    0.44
    ownership
    0.44
     although
    0.43
    MV
    0.42
    را
    0.42
    ره
    0.42
    c
    0.42
    Activations Density 0.000%

    No Known Activations