© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48384
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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_40_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
    <unused301>
    0.51
    ৩৮
    0.50
    <unused525>
    0.47
    <unused481>
    0.45
     October
    0.45
    ﺤ
    0.45
    tpVar
    0.44
    <unused369>
    0.44
    <unused640>
    0.44
    ৪৪
    0.44
    POSITIVE LOGITS
     diarios
    0.38
    ived
    0.36
     rivals
    0.36
    ierra
    0.34
    urra
    0.34
    uese
    0.34
    atan
    0.33
     தினத்தன்று
    0.33
    tete
    0.33
    imba
    0.33
    Activations Density 0.009%

    No Known Activations