© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2461
    Prev
    Next
    INDEX
    Explanations

    i after numbers or vowels

    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_16_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
    5
    0.55
    3
    0.53
    ärke
    0.52
    1
    0.51
    oną
    0.50
    𝐟
    0.47
    4
    0.46
    webBrowser
    0.46
    นำ
    0.45
    passive
    0.45
    POSITIVE LOGITS
     I
    0.56
     it
    0.56
     You
    0.55
     It
    0.53
     pedir
    0.51
    ار
    0.50
     angrily
    0.46
     perceber
    0.46
    فكير
    0.44
    zinho
    0.44
    Activations Density 0.432%

    No Known Activations