© 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. 4884
    Prev
    Next
    INDEX
    Explanations

    know if

    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
     freestanding
    2.12
     makeSound
    1.93
    discrete
    1.91
     masculine
    1.88
    7
    1.86
    Discrete
    1.83
    rinsic
    1.81
    6
    1.81
     decentralized
    1.79
    3
    1.79
    POSITIVE LOGITS
     historians
    2.02
    タック
    1.85
    ouncement
    1.83
     shenanigans
    1.82
     arrows
    1.80
     disease
    1.79
     news
    1.79
     scheme
    1.77
     organisation
    1.75
     hits
    1.75
    Activations Density 0.051%

    No Known Activations