© 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-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 110212
    Prev
    Next
    INDEX
    Explanations

    core compensation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ण्
    0.49
     Recorder
    0.46
     কর্নেল
    0.46
    फ्ल
    0.46
    주
    0.46
    isierung
    0.45
    Engel
    0.45
    キー
    0.45
    Cuáles
    0.45
    elman
    0.44
    POSITIVE LOGITS
     acontecer
    0.47
     ó
    0.46
    					
    0.44
    प्रदेश
    0.43
     tappa
    0.42
    roveň
    0.42
     fra
    0.41
                    
    0.41
     আগ
    0.41
     ò
    0.41
    Activations Density 0.002%

    No Known Activations