© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11885
    Prev
    Next
    INDEX
    Explanations

    past tense specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innego
    1.41
    и
    1.31
    iguity
    1.27
    luoromethyl
    1.23
    stige
    1.21
     Geç
    1.20
     gotta
    1.19
    ጨማሪ
    1.17
    ப்பட்ட
    1.16
    கடந்த
    1.16
    POSITIVE LOGITS
     hills
    1.36
     herds
    1.20
     taxis
    1.20
    រ
    1.15
     overthrown
    1.13
    BtnPanel
    1.13
     shawl
    1.12
     minDist
    1.11
    Ἠ
    1.11
     legs
    1.11
    Activations Density 0.000%

    No Known Activations