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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41460
    Prev
    Next
    INDEX
    Explanations

    alphabet, numerals, roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite

    single letters as labels or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ใน
    0.50
    аб
    0.50
     вико
    0.50
    i
    0.49
     కొన్ని
    0.47
    ବା
    0.47
     OFFIC
    0.47
    nesse
    0.46
    ви
    0.45
    ቱም
    0.45
    POSITIVE LOGITS
    හා
    0.44
     учё
    0.42
    hljs
    0.42
     antaranya
    0.42
     نج
    0.42
    ගෙන
    0.41
    高齢
    0.41
    0
    0.41
     न्यूजीलैंड
    0.41
    \
    0.40
    Activations Density 0.000%

    No Known Activations