© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4845
    Prev
    Next
    INDEX
    Explanations

    payment systems

    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
    циа
    1.60
    Aub
    1.55
    7
    1.55
    ambient
    1.54
     Rai
    1.49
     Alexa
    1.49
     Alba
    1.49
     ABA
    1.48
     Aub
    1.46
    6
    1.45
    POSITIVE LOGITS
     warned
    0.83
     reckons
    0.81
    }={
    0.79
     proof
    0.76
    mard
    0.76
     historians
    0.72
    舛
    0.72
    )}=\
    0.71
     Vou
    0.71
     commas
    0.71
    Activations Density 0.000%

    No Known Activations