© 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. 61002
    Prev
    Next
    INDEX
    Explanations

    contrasting options and limitations

    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
     transitioned
    0.45
     Ui
    0.45
    目标的
    0.44
    সভায়
    0.42
    😥
    0.42
     colorChoice
    0.42
    ģ
    0.42
    <0x8C>
    0.42
    șit
    0.41
    建议
    0.41
    POSITIVE LOGITS
    ing
    0.48
     کر
    0.46
    haj
    0.45
     เด่น
    0.45
    brane
    0.45
    t
    0.45
    ovat
    0.45
    da
    0.44
     \&
    0.43
     вони
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.