© 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. 135599
    Prev
    Next
    INDEX
    Explanations

    Isn’t It Romantic; Invitational Tournament

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

    conditional explanations

    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
    L
    0.51
    ავ
    0.49
    荞
    0.47
    蕎
    0.47
    ե
    0.46
    <0xC7>
    0.46
    Ꮭ
    0.46
    https
    0.45
    可以
    0.44
    小説
    0.44
    POSITIVE LOGITS
     acumin
    0.47
     ترم
    0.46
    ()==
    0.42
     lateribus
    0.42
     свобо
    0.42
    tevõ
    0.41
     divaricatis
    0.41
     ASX
    0.41
     тела
    0.41
     متنوع
    0.40
    Activations Density 0.001%

    No Known Activations