© 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. 15-GEMMASCOPE-2-RES-262K
    7. 70480
    Prev
    Next
    INDEX
    Explanations

    never forget or seen, to put

    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_15_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
    apen
    1.83
     kich
    1.82
    IMIT
    1.79
    장
    1.79
     kadar
    1.78
     fark
    1.78
     maxX
    1.78
    𝚑
    1.77
    恐惧
    1.77
    quanto
    1.76
    POSITIVE LOGITS
     meestal
    0.75
     fromi
    0.74
     sourced
    0.70
    roversial
    0.70
     otherwise
    0.66
    generic
    0.65
     ordinarily
    0.63
    typically
    0.62
     from
    0.62
     دینا
    0.62
    Activations Density 0.001%

    No Known Activations