© 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. 200544
    Prev
    Next
    INDEX
    Explanations

    processing incoming messages

    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
    Catherine
    0.45
    Was
    0.43
    typography
    0.43
    分子
    0.43
    resistance
    0.42
    Liberty
    0.41
    損
    0.41
    Francis
    0.41
    US
    0.41
    a
    0.41
    POSITIVE LOGITS
     regelmäßig
    0.55
     memperhatikan
    0.54
     regularmente
    0.54
    azam
    0.51
     allongé
    0.50
     détect
    0.49
     perangkat
    0.49
     cihaz
    0.48
     memasuki
    0.48
    aktif
    0.48
    Activations Density 0.006%

    No Known Activations