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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    もの
    1.38
     tide
    1.28
     one
    1.26
     chapters
    1.25
     older
    1.21
    !<
    1.20
    ον
    1.20
    ofil
    1.19
    他在
    1.19
     patient
    1.18
    POSITIVE LOGITS
     =
    2.24
     =",
    1.76
     +=
    1.70
     &=
    1.60
    τηση
    1.56
     ={
    1.56
     :=
    1.51
     /=
    1.44
    性は
    1.42
     -=
    1.40
    Activations Density 0.714%

    No Known Activations