© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14256
    Prev
    Next
    INDEX
    Explanations

    concession or contrast

    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
    DebugSymbols
    2.81
    ност
    2.77
    teki
    2.73
    sto
    2.64
    𝘭
    2.63
    ന്ത്രാ
    2.60
     гори
    2.59
     vak
    2.56
    nlü
    2.51
     poni
    2.45
    POSITIVE LOGITS
    {@
    2.77
    మం
    2.66
    แหน
    2.46
    пря
    2.26
    iteks
    2.25
    的
    2.25
    ̡
    2.24
     Doch
    2.24
    ==============]
    2.23
     Booster
    2.19
    Activations Density 0.009%

    No Known Activations