© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    turn transitions and list items

    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
    3.05
    6
    2.93
    3
    2.89
    8
    2.87
    4
    2.67
    5
    2.57
    rinsic
    2.47
    9
    2.47
    quetas
    2.25
    ٦
    2.16
    POSITIVE LOGITS
     (’
    2.04
     rém
    1.88
    )}=\
    1.83
     historians
    1.77
     (=
    1.77
     præ
    1.76
     Cllr
    1.74
     leaks
    1.72
     (£
    1.69
     adjournment
    1.67
    Activations Density 0.000%

    No Known Activations