© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3457
    Prev
    Next
    INDEX
    Explanations

    calcium, osteoporosis, milking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    铆
    1.15
    嗅
    1.04
    idazole
    1.03
     cloth
    1.03
     MZ
    0.98
    dropna
    0.96
    rune
    0.96
     decorated
    0.96
     trumpet
    0.96
     Tup
    0.95
    POSITIVE LOGITS
    Calcium
    1.69
     Calcium
    1.58
     calcium
    1.38
    牛乳
    1.27
     Bullock
    1.23
    鈣
    1.22
     Limestone
    1.15
     osteoporosis
    1.10
    カルシ
    1.10
     Osm
    1.09
    Activations Density 0.014%

    No Known Activations