© 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. 15052
    Prev
    Next
    INDEX
    Explanations

    hundreds thousands millions

    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
     an
    0.63
     väga
    0.63
     was
    0.62
     e
    0.55
     approximately
    0.54
     at
    0.54
     noin
    0.54
     on
    0.53
     vino
    0.51
     anemia
    0.51
    POSITIVE LOGITS
     centena
    0.71
     decena
    0.68
    lerce
    0.64
     decenas
    0.63
     hundreds
    0.63
    \
    0.63
     тысяч
    0.62
    Hundreds
    0.62
     thousands
    0.61
    Tens
    0.60
    Activations Density 0.010%

    No Known Activations