© 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. 5160
    Prev
    Next
    INDEX
    Explanations

    programming, code, technical terms

    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
    Negative Logits
    quetas
    1.61
    rinsic
    1.59
     satuan
    1.45
     Poa
    1.42
    abhavo
    1.41
    }^{+}
    1.41
     Guadalupe
    1.40
     itemView
    1.40
    }^{+},
    1.39
     mimetype
    1.39
    POSITIVE LOGITS
    Cast
    1.38
     Railway
    1.36
    Rust
    1.35
     Cast
    1.33
    (
    1.31
     historians
    1.27
    cast
    1.25
     News
    1.24
    Word
    1.22
    Col
    1.20
    Activations Density 0.023%

    No Known Activations