© 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. 241015
    Prev
    Next
    INDEX
    Explanations

    for many truly

    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
    dates
    0.51
    mern
    0.49
     اربعه
    0.48
    憉
    0.46
     रखो
    0.46
     foram
    0.44
     tensors
    0.44
    榫
    0.44
    ierra
    0.44
    ۀ
    0.44
    POSITIVE LOGITS
    1
    0.46
    6
    0.46
    ”
    0.46
    legg
    0.45
    )
    0.42
    сит
    0.42
    רג
    0.42
    סה
    0.41
     repentance
    0.41
    里克
    0.41
    Activations Density 0.000%

    No Known Activations