© 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-16K
    7. 2048
    Prev
    Next
    INDEX
    Explanations

    public services and software development

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     homosexuality
    1.29
     curls
    1.23
     amores
    1.23
    ifiers
    1.22
    osexuality
    1.22
    ἡ
    1.20
     favoritos
    1.20
     붙
    1.19
    loving
    1.18
    Curl
    1.18
    POSITIVE LOGITS
     public
    1.18
     portfolios
    1.13
     stakeholder
    1.12
     Public
    1.08
     scalability
    1.06
     dashboard
    1.06
    public
    1.05
     عوامی
    1.04
    サーバ
    1.02
    <0x0D>
    1.01
    Activations Density 0.330%

    No Known Activations