© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3330
    Prev
    Next
    INDEX
    Explanations

    descriptive prefixes and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Em
    0.66
    સિંહ
    0.65
    শ্বর
    0.65
     ಔಷ
    0.65
    ఇ
    0.64
    Alz
    0.63
    डियो
    0.63
    دون
    0.62
    Alcohol
    0.61
     состояния
    0.61
    POSITIVE LOGITS
    ider
    0.76
    eworthy
    0.66
    itted
    0.62
    е
    0.62
    并在
    0.61
    ido
    0.58
    ared
    0.58
    enting
    0.58
    acht
    0.56
    \'
    0.56
    Activations Density 0.083%

    No Known Activations