© 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. 158723
    Prev
    Next
    INDEX
    Explanations

    specific words followed by to

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

    captures or matches

    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
    '
    0.52
    ыска
    0.48
    ạt
    0.47
    시
    0.47
    abella
    0.46
     optimizes
    0.46
    łem
    0.46
    arantad
    0.45
    ത്ത്
    0.45
    ēj
    0.45
    POSITIVE LOGITS
     เหมือน
    0.46
    you
    0.44
     هم
    0.43
     UnwrapRef
    0.42
     ވަ
    0.41
     వచ్చి
    0.40
    เหมือน
    0.40
    ໜ
    0.40
     Smooth
    0.40
    smo
    0.40
    Activations Density 0.001%

    No Known Activations