© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8661
    Prev
    Next
    INDEX
    Explanations

    imagine a scenario

    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_17_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
    जनबी
    1.35
     declarado
    1.09
     resc
    1.08
     empr
    1.07
     terhadap
    1.06
    A
    1.04
     est
    1.02
     agama
    1.00
     escritos
    1.00
    ″
    0.98
    POSITIVE LOGITS
    tım
    1.73
     imagines
    1.69
     imagined
    1.69
    搬型
    1.65
     envisions
    1.65
     vividly
    1.63
    future
    1.46
    ໄລ
    1.45
     Sicily
    1.43
    ﻖ
    1.43
    Activations Density 0.214%

    No Known Activations