© 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. 103975
    Prev
    Next
    INDEX
    Explanations

    about gossip

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

    transforming other things into

    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
    if
    0.47
    Τ
    0.45
    。
    0.43
    utus
    0.42
    т
    0.42
    ।
    0.41
     descriptor
    0.40
     présents
    0.40
     angered
    0.40
     ingested
    0.39
    POSITIVE LOGITS
     বাগ
    0.48
     ಆಯ್
    0.47
     дошко
    0.47
    繽
    0.46
     гара
    0.46
     라는
    0.45
     เซ
    0.45
     தேர்ந்த
    0.44
     പാർ
    0.44
     gått
    0.44
    Activations Density 0.001%

    No Known Activations