© 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-65K
    7. 7988
    Prev
    Next
    INDEX
    Explanations

    from afar

    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_65k_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
     інших
    0.39
    沏
    0.38
     innych
    0.36
     శరీ
    0.36
     ரே
    0.36
     postérieur
    0.36
    żenie
    0.35
     striées
    0.35
     λά
    0.35
     რომელიც
    0.35
    POSITIVE LOGITS
     the
    0.56
     its
    0.43
     a
    0.36
    the
    0.35
    \
    0.34
     whatever
    0.32
     afar
    0.32
     wildfire
    0.32
     and
    0.31
     separate
    0.31
    Activations Density 0.050%

    No Known Activations