© 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. 38770
    Prev
    Next
    INDEX
    Explanations

    |

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

    classifying languages or algorithms

    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
    ra
    0.47
    la
    0.46
     ensuing
    0.43
     ቡ
    0.42
    3
    0.42
    8
    0.42
    apur
    0.41
    ..
    0.40
    range
    0.40
    ..............
    0.39
    POSITIVE LOGITS
     شائع
    0.49
     અથવા
    0.44
    橱
    0.43
    म्यान
    0.42
    جات
    0.42
    مثل
    0.42
    িকায়
    0.41
    तियाँ
    0.41
    روش
    0.41
     stöd
    0.41
    Activations Density 0.000%

    No Known Activations