© 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. 154636
    Prev
    Next
    INDEX
    Explanations

    travel and titles

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

    combinations of words

    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
     continuer
    0.51
     ザ
    0.48
     odred
    0.46
     ತುಂಬಾ
    0.46
     حاول
    0.45
    mead
    0.45
     這
    0.45
     vengan
    0.45
     نحاول
    0.45
    meas
    0.44
    POSITIVE LOGITS
    节目
    0.45
     Ambassador
    0.42
     matches
    0.41
    মন্ত্রী
    0.41
    ด
    0.39
    대로
    0.39
     Scalars
    0.39
    ü
    0.39
    CopyTo
    0.39
    เยี่ยม
    0.38
    Activations Density 0.002%

    No Known Activations