© 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. 16-GEMMASCOPE-2-RES-262K
    7. 43690
    Prev
    Next
    INDEX
    Explanations

    holy followed by exclamation or title

    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_262k_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
    し
    0.66
    ة
    0.65
    らない
    0.55
    рь
    0.51
    і
    0.50
     ፣
    0.49
    い
    0.49
    ,\
    0.49
     blurring
    0.47
     coars
    0.47
    POSITIVE LOGITS
    comstock
    0.56
    VICIO
    0.53
     declares
    0.53
    Ƌ
    0.53
     sAlarm
    0.51
    Ɔ
    0.51
    ಾರ್
    0.50
    años
    0.50
    NP
    0.50
    TS
    0.49
    Activations Density 0.000%

    No Known Activations