© 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. 3325
    Prev
    Next
    INDEX
    Explanations

    list and companies

    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
    7
    1.89
    6
    1.79
    8
    1.77
    4
    1.65
    5
    1.61
    3
    1.58
    0
    1.48
    9
    1.48
    2
    1.38
    1
    1.16
    POSITIVE LOGITS
     rém
    1.79
     selectors
    1.53
    ジュ
    1.51
     Ramb
    1.47
     orthodont
    1.47
     schemes
    1.47
     Gal
    1.45
    )}=\
    1.45
    筵
    1.44
     gover
    1.44
    Activations Density 0.201%

    No Known Activations