© 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. 209563
    Prev
    Next
    INDEX
    Explanations

    status updates and ongoing work

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

    history, growth, and development

    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
    úsica
    0.53
     শুরুতে
    0.50
    重複
    0.47
     HTMLSc
    0.46
    <0x91>
    0.46
     ponctués
    0.45
     Noise
    0.44
     repetitions
    0.44
     دين
    0.44
     Sheep
    0.43
    POSITIVE LOGITS
    P
    0.61
    R
    0.52
     sone
    0.50
     diri
    0.49
    大家好
    0.47
     protagonisti
    0.47
    T
    0.47
    C
    0.47
    V
    0.47
    hti
    0.47
    Activations Density 0.000%

    No Known Activations