© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 613
    Prev
    Next
    INDEX
    Explanations

    Wuthering Heights

    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
    the
    0.64
    an
    0.63
     Elektrokh
    0.61
    와
    0.58
    ्स
    0.57
     PWMB
    0.57
     carcinomas
    0.56
    ੀ
    0.52
     мастеров
    0.51
     hairstyles
    0.50
    POSITIVE LOGITS
     to
    0.96
    el
    0.84
     en
    0.82
    ل
    0.80
     anvä
    0.78
    ab
    0.76
     $\
    0.76
     geçer
    0.74
    ppure
    0.71
    した
    0.69
    Activations Density 0.003%

    No Known Activations