© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9172
    Prev
    Next
    INDEX
    Explanations

    instructional materials

    np_acts-logits-general · gemini-2.5-flash-lite

    instruction following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    位于
    0.40
    anais
    0.39
     BAN
    0.38
    namely
    0.38
    位於
    0.38
    হি
    0.37
    atering
    0.37
    ㅌ
    0.37
    setPreferred
    0.37
    销售
    0.36
    POSITIVE LOGITS
     instructional
    0.45
     crystals
    0.42
     dri
    0.42
     drip
    0.39
     laced
    0.38
     болот
    0.38
    ினாலும்
    0.38
     Instructional
    0.37
     pellets
    0.37
     Александр
    0.37
    Activations Density 0.064%

    No Known Activations