© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14377
    Prev
    Next
    INDEX
    Explanations

    Alphabet and higher power

    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_7_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
    Открыть
    2.16
    ပိုင်း
    2.16
     Comun
    2.13
     perde
    2.12
    ১
    2.10
     baixa
    2.08
    帼
    2.06
    šel
    2.04
     continueRoutine
    2.02
    散
    2.00
    POSITIVE LOGITS
    ljeni
    2.44
    makeConstraints
    2.43
    ele
    2.28
    erah
    2.26
    KeyPress
    2.24
    dad
    2.20
    hline
    2.20
    tid
    2.16
    eig
    2.15
    paar
    2.15
    Activations Density 0.026%

    No Known Activations