© 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. 24820
    Prev
    Next
    INDEX
    Explanations

    of course, obviously

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

    obviously, naturally, of course

    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
     pourtant
    0.54
     ಸುಮ
    0.53
     surprisingly
    0.52
     Surprisingly
    0.49
    居然
    0.49
     reportedly
    0.48
    虽
    0.47
    似乎
    0.47
    Truly
    0.45
     aproximadamente
    0.45
    POSITIVE LOGITS
     oczywiście
    1.16
     natürlich
    1.14
    当然
    1.11
     당연
    1.09
    當然
    1.09
     évidemment
    1.07
     ovviamente
    1.06
     natuurlijk
    1.03
     obviously
    0.96
     obviamente
    0.96
    Activations Density 0.165%

    No Known Activations