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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9653
    Prev
    Next
    INDEX
    Explanations

    defining essence or purpose

    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_9_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
    similar
    1.44
    k
    1.32
     verwendet
    1.32
     anteriormente
    1.30
    is
    1.26
    as
    1.25
    anha
    1.25
    ைட்
    1.23
    ı
    1.22
    э
    1.21
    POSITIVE LOGITS
     decisões
    1.75
     Chirurgien
    1.58
     tarsi
    1.54
     preven
    1.51
    𝗢
    1.49
     boje
    1.43
     leren
    1.43
    र्गत
    1.41
     apprendre
    1.41
     sikap
    1.41
    Activations Density 0.247%

    No Known Activations