© 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. 30925
    Prev
    Next
    INDEX
    Explanations

    incrementing or assigning variables

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

    tracking cumulative progression

    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
    泬
    0.40
    blow
    0.39
    ắng
    0.39
     בן
    0.39
    acher
    0.38
    댄
    0.37
    ét
    0.36
    ừ
    0.36
    骂
    0.36
    灼
    0.36
    POSITIVE LOGITS
     developing
    0.43
    Increasing
    0.42
     ++)
    0.41
    Developing
    0.41
     incrementar
    0.40
    ++)
    0.40
    ++,
    0.39
    structor
    0.38
    どんどん
    0.38
     increasing
    0.38
    Activations Density 0.000%

    No Known Activations