© 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. 110729
    Prev
    Next
    INDEX
    Explanations

    graduated from, friends, lobby

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

    AI resurgence understanding audience

    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
    time
    0.47
    array
    0.47
     ਸਮ
    0.47
    way
    0.45
    fea
    0.45
     શક્ય
    0.45
     ########.
    0.44
     모든
    0.44
     액세
    0.44
     時
    0.44
    POSITIVE LOGITS
     cittam
    0.49
     prosthesis
    0.44
    िखित
    0.43
     justement
    0.42
    ल्यानंतर
    0.42
    しっかりと
    0.42
     viewership
    0.42
     prej
    0.42
    剣
    0.41
    ้อย
    0.41
    Activations Density 0.000%

    No Known Activations