© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14774
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_22_width_262k_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
    ⁩
    0.84
     digging
    0.80
     __(
    0.76
     Бек
    0.76
     другом
    0.74
     Solidarity
    0.73
     DAC
    0.71
    <unused2100>
    0.70
    mediaDevices
    0.69
     Осо
    0.69
    POSITIVE LOGITS
    ya
    0.70
    Templates
    0.70
    Nintendo
    0.67
    Quantum
    0.66
    Loop
    0.66
     സാ
    0.65
    泯
    0.65
    Hybrid
    0.65
    จบ
    0.65
    Rak
    0.64
    Activations Density 0.066%

    No Known Activations