© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7539
    Prev
    Next
    INDEX
    Explanations

    cities, but no houses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    ل
    1.49
    Diese
    1.40
    ጨማሪ
    1.37
     Każ
    1.34
     pretože
    1.34
     Diese
    1.32
    لما
    1.31
     انا
    1.31
    ખ્ય
    1.31
    ल्डर
    1.31
    POSITIVE LOGITS
     rectification
    1.13
     pl
    1.11
     mores
    1.02
    residual
    1.01
    (-
    1.01
     compared
    0.99
    rew
    0.99
     (~
    0.98
     rupture
    0.97
    rove
    0.96
    Activations Density 0.000%

    No Known Activations