© 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-16K
    7. 10242
    Prev
    Next
    INDEX
    Explanations

    por qué, por lo tanto

    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_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
     manner
    0.87
     latter
    0.82
    д
    0.77
    ય
    0.77
    യാണ്
    0.73
     आयाम
    0.73
    ende
    0.73
    ndarray
    0.72
     través
    0.72
    Ва
    0.72
    POSITIVE LOGITS
    cupine
    1.60
    centaje
    1.17
    ல்
    1.14
    celain
    1.11
    ridge
    1.10
     debajo
    1.10
    ity
    1.07
    菟
    1.04
    damping
    1.04
     ejemplo
    1.02
    Activations Density 0.042%

    No Known Activations