© 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. 247490
    Prev
    Next
    INDEX
    Explanations

    "the" followed by Spotify, North, CAT, OS

    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
     setToDefault
    0.60
    𝔬
    0.59
     elő
    0.58
    نې
    0.57
     względu
    0.56
     uitvo
    0.54
     мә
    0.52
    راہیم
    0.51
    
    0.51
    সকল
    0.50
    POSITIVE LOGITS
    ↵↵
    0.63
    ind
    0.55
    ud
    0.55
    strength
    0.55
    af
    0.54
    active
    0.54
    fin
    0.54
    DF
    0.54
    ise
    0.53
    version
    0.53
    Activations Density 0.000%

    No Known Activations