© 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. 51060
    Prev
    Next
    INDEX
    Explanations

    acknowledging, loosening, guides, allows

    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
    ላት
    0.46
     embaixo
    0.44
    מים
    0.44
    PreferredItem
    0.43
    背后
    0.43
    ستی
    0.42
    姍
    0.41
    蟆
    0.41
    աստ
    0.41
    ሮች
    0.41
    POSITIVE LOGITS
    D
    0.46
    PP
    0.44
    X
    0.40
    TM
    0.37
     scaler
    0.37
    ks
    0.37
    td
    0.36
    π
    0.36
    0.36
    tm
    0.35
    Activations Density 0.002%

    No Known Activations