© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9225
    Prev
    Next
    INDEX
    Explanations

    like you or like these

    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
     INKA
    1.60
    ाइम
    1.52
    ैट
    1.51
    श्मीर
    1.50
     ricotta
    1.48
     trás
    1.46
    ℕ
    1.45
    Paxos
    1.41
     realization
    1.40
     Advisory
    1.40
    POSITIVE LOGITS
    naire
    1.42
    માં
    1.42
    emd
    1.40
    undo
    1.39
    ]%
    1.38
    ล์
    1.37
    +](=
    1.35
     כי
    1.34
    \.
    1.33
     დროს
    1.33
    Activations Density 0.000%

    No Known Activations