© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10255
    Prev
    Next
    INDEX
    Explanations

    follow instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
    {
    0.65
    ;
    0.62
    ⒏
    0.58
    _<
    0.57
     outlying
    0.57
     hled
    0.56
    <0x9F>
    0.55
     aprovech
    0.54
    __.
    0.54
     thẻ
    0.53
    POSITIVE LOGITS
     follow
    1.07
    follow
    0.99
    Follow
    0.96
     Follow
    0.94
    follows
    0.88
     follows
    0.86
     suivre
    0.84
     suivent
    0.80
     অনুসরণ
    0.79
     followup
    0.79
    Activations Density 0.119%

    No Known Activations