© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9690
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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_31_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
     as
    0.35
    ដែល
    0.31
    .
    0.31
     but
    0.30
    3
    0.29
     irradiated
    0.29
     I
    0.28
    9
    0.28
    lf
    0.28
    6
    0.27
    POSITIVE LOGITS
     perusahaan
    0.38
     gobierno
    0.36
     பிரச்
    0.35
     relacionamento
    0.34
    iya
    0.33
     cierta
    0.32
    咱们
    0.32
    odyne
    0.32
     dokter
    0.31
    𝑧
    0.31
    Activations Density 0.098%

    No Known Activations