© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71572
    Prev
    Next
    INDEX
    Explanations

    chaotic haven; synonym replacement; Satellite Imagery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     remedial
    0.46
     τρόπο
    0.43
     metaphorical
    0.41
     MacL
    0.40
     सीखने
    0.39
     Remed
    0.38
     découverte
    0.38
    悛
    0.38
     அவர்களுடைய
    0.38
     découvert
    0.37
    POSITIVE LOGITS
     altas
    0.46
    :^(
    0.46
    мат
    0.45
     protr
    0.45
    d
    0.45
     interf
    0.45
    vamo
    0.45
     stunned
    0.44
     Beatriz
    0.44
    Х
    0.43
    Activations Density 0.006%

    No Known Activations