© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219981
    Prev
    Next
    INDEX
    Explanations

    access, rejection, further, experience

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign characters and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     النار
    0.45
     mustered
    0.45
     جماعت
    0.44
     terrified
    0.44
    篂
    0.43
     mali
    0.42
     exemplos
    0.41
     şeyler
    0.41
    baixo
    0.41
     encima
    0.40
    POSITIVE LOGITS
    DAQ
    0.49
    變化
    0.45
    德
    0.44
     EEG
    0.41
     आरक्षण
    0.41
     加入
    0.41
     वायरलेस
    0.41
    КТ
    0.41
    DEA
    0.41
    də
    0.41
    Activations Density 0.000%

    No Known Activations