© 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. 4769
    Prev
    Next
    INDEX
    Explanations

    definitions and recommendations

    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
    ributes
    2.05
     Kalam
    2.04
    𝑬
    1.99
    lection
    1.98
     vittoria
    1.95
    outfile
    1.91
     repay
    1.84
    늬
    1.82
     mastectomy
    1.78
    ivered
    1.77
    POSITIVE LOGITS
     Matic
    1.80
     ridiculus
    1.79
    Controllers
    1.70
     untenable
    1.57
    леку
    1.51
    หมาย
    1.49
    amentos
    1.46
    ほしい
    1.41
     hmot
    1.41
    getto
    1.38
    Activations Density 0.041%

    No Known Activations