© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93584
    Prev
    Next
    INDEX
    Explanations

    constant, positive, kindness

    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_31_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
     Voyager
    0.44
    o
    0.43
     Vox
    0.42
    orat
    0.42
     nucleotides
    0.41
     Voyage
    0.41
    ار
    0.41
     URI
    0.40
     Arund
    0.40
    서
    0.40
    POSITIVE LOGITS
     nuestra
    0.44
     ટે
    0.44
    rello
    0.44
     повышение
    0.44
    Club
    0.44
    ប៉
    0.43
    ilaian
    0.43
    បែប
    0.43
    NotBlank
    0.43
     свободно
    0.43
    Activations Density 0.006%

    No Known Activations