© 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. 105596
    Prev
    Next
    INDEX
    Explanations

    award and allocated items

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

    typed array

    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
    ᄄ
    0.45
    stum
    0.44
    𝑓
    0.44
    arın
    0.44
     cohom
    0.44
    ेडकर
    0.44
    ᄃ
    0.44
    ၄
    0.43
    ᱯ
    0.43
    aros
    0.43
    POSITIVE LOGITS
     awarded
    0.46
    ത്തിനായി
    0.46
     regretted
    0.44
     allocates
    0.43
     medallion
    0.42
     awarding
    0.42
    طة
    0.41
     yelled
    0.41
     disclosed
    0.41
    SIGNED
    0.41
    Activations Density 0.000%

    No Known Activations