© 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. 88971
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

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

    ability, inability, ambiguity

    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
    ل
    0.66
    ד
    0.59
    л
    0.54
    все
    0.48
     тыся
    0.46
    Ис
    0.46
     売
    0.45
     sepd
    0.45
     przech
    0.45
     ومع
    0.45
    POSITIVE LOGITS
     vento
    0.49
    (
    0.47
     ভেতরে
    0.45
     reporting
    0.45
     washout
    0.45
     Marte
    0.43
     graceful
    0.41
    deviceID
    0.41
     ν
    0.41
    ืน
    0.41
    Activations Density 0.000%

    No Known Activations