© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2171
    Prev
    Next
    INDEX
    Explanations

    asking what can be done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    A
    1.31
    Okay
    1.18
     ничего
    1.10
    ό
    1.08
    B
    1.06
     Okay
    1.06
    рите
    1.04
    totally
    1.03
    u
    1.03
     Totally
    1.03
    POSITIVE LOGITS
     happens
    1.83
    देशीर
    1.76
    soever
    1.68
     else
    1.66
     happened
    1.59
     transpired
    1.51
     constitutes
    1.43
     happen
    1.41
    ുകൊണ്ടാണ്
    1.39
     percentage
    1.39
    Activations Density 0.635%

    No Known Activations