© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2165
    Prev
    Next
    INDEX
    Explanations

    applied to a variety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     (’
    1.69
     organisers
    1.48
     astronomers
    1.46
    ぎ
    1.45
     trou
    1.44
     historians
    1.43
     (“
    1.41
     entertained
    1.37
     wherever
    1.37
    タック
    1.35
    POSITIVE LOGITS
    7
    2.41
    6
    2.14
    5
    2.10
    8
    2.08
    9
    2.06
    4
    2.01
    3
    1.96
    0
    1.90
     karen
    1.75
    /?
    1.67
    Activations Density 0.098%

    No Known Activations