© 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. 26168
    Prev
    Next
    INDEX
    Explanations

    dates and time periods

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

    multi-language content

    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
     Meeting
    0.57
    𝐞
    0.56
    oe
    0.55
    of
    0.53
     吴
    0.52
    oc
    0.51
    ji
    0.50
     Ek
    0.50
    ｅ
    0.49
    orez
    0.49
    POSITIVE LOGITS
    ージー
    0.48
    Raises
    0.46
    劇場
    0.44
    ویزی
    0.43
     iā
    0.43
    charg
    0.41
    ጠበ
    0.41
    ඪ
    0.41
    待ち
    0.41
    あらゆる
    0.40
    Activations Density 0.000%

    No Known Activations