© 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. 10706
    Prev
    Next
    INDEX
    Explanations

    postal codes and addresses

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

    street address postal codes

    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
     Anime
    0.51
    fungen
    0.45
    ajemen
    0.44
     মেশিন
    0.43
    ähne
    0.42
    ጷ
    0.42
     तकनीक
    0.41
    品牌的
    0.41
    Anime
    0.41
     しっかり
    0.41
    POSITIVE LOGITS
    Ü
    0.47
    ա
    0.46
     hilltop
    0.46
     С
    0.45
    A
    0.44
     postal
    0.44
    с
    0.43
     pitches
    0.43
     окре
    0.42
    இ
    0.42
    Activations Density 0.010%

    No Known Activations