© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135279
    Prev
    Next
    INDEX
    Explanations

    artists, songs, lyrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     দৃশ্য
    0.47
     Oiseau
    0.47
     Hopl
    0.47
     Kowloon
    0.47
    Disco
    0.46
     Stras
    0.46
    廰
    0.46
     Astronomy
    0.45
    峴
    0.45
    scene
    0.44
    POSITIVE LOGITS
    anyahu
    0.48
    orghini
    0.46
     lavish
    0.45
     wrath
    0.44
     spotless
    0.42
    adona
    0.42
     बादशाह
    0.42
     supremacy
    0.42
     poderos
    0.41
     Benzema
    0.41
    Activations Density 0.003%

    No Known Activations