© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 133686
    Prev
    Next
    INDEX
    Explanations

    will, would, am not, He know

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

    body part or object

    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
     Bldg
    0.55
     perfeito
    0.53
    আপনি
    0.48
     школе
    0.48
     বিদ্যালয়
    0.47
    䏹
    0.46
    兢
    0.46
     योर
    0.46
     thoughtfully
    0.45
     করিতেছিল
    0.45
    POSITIVE LOGITS
     synchron
    0.47
     categor
    0.46
     scanty
    0.44
     apopt
    0.44
     imbalance
    0.43
     app
    0.43
     (
    0.43
     pseudo
    0.42
     hostages
    0.42
     rewritten
    0.41
    Activations Density 0.002%

    No Known Activations