© 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. 222773
    Prev
    Next
    INDEX
    Explanations

    appreciated or Luke Skywalker

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

    number sequences and units

    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
     자신의
    0.49
     Kabhi
    0.45
    å
    0.43
     अपनी
    0.43
     हिस्सा
    0.42
    xsi
    0.42
     ਆਪਣੇ
    0.41
     kendi
    0.40
     kamm
    0.40
     आफ्नो
    0.40
    POSITIVE LOGITS
    ?’
    0.50
     visitantes
    0.50
    ؟
    0.50
     Bunker
    0.49
    ?'
    0.46
     إذا
    0.46
     LID
    0.46
     ferrug
    0.45
     Facilities
    0.45
     أعلام
    0.45
    Activations Density 0.000%

    No Known Activations