© 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. 2806
    Prev
    Next
    INDEX
    Explanations

    for a purpose

    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
    0.34
    5
    0.33
     dieser
    0.32
     Finest
    0.30
    ，”
    0.30
    6
    0.30
     Regis
    0.30
    E
    0.30
     liga
    0.29
    的
    0.29
    POSITIVE LOGITS
     from
    0.44
    tc
    0.41
    tól
    0.41
    tp
    0.41
    𝕕
    0.40
    ला
    0.39
    ye
    0.39
    kę
    0.39
    ʣ
    0.38
    乆
    0.38
    Activations Density 0.671%

    No Known Activations