© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3621
    Prev
    Next
    INDEX
    Explanations

    physical descriptors for stone and rock

    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_29_width_16k_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
     Pfaff
    0.76
     बनर्जी
    0.73
     ευ
    0.70
     Lenz
    0.70
     Saras
    0.70
    秧
    0.68
    벌
    0.68
     शुक्ला
    0.67
     VLAN
    0.66
    sweet
    0.65
    POSITIVE LOGITS
     stones
    4.06
     stone
    4.05
     rocks
    3.81
     rock
    3.62
     Stone
    3.54
     Stones
    3.44
    石
    3.35
    Stone
    3.34
    石头
    3.28
    石頭
    3.25
    Activations Density 0.313%

    No Known Activations