© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1578
    Prev
    Next
    INDEX
    Explanations

    metaphorical nouns associated with abstract concepts

    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_16_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
    x
    0.51
    ı
    0.50
    q
    0.49
    ;
    0.47
    ills
    0.45
    ants
    0.45
    iff
    0.44
    ?
    0.44
    tt
    0.44
     aprovechar
    0.43
    POSITIVE LOGITS
     Scuola
    0.49
     scuole
    0.42
     clinician
    0.41
     Has
    0.40
    RFID
    0.40
     gentamicin
    0.40
     Độ
    0.39
     nitrile
    0.39
     Fernandes
    0.38
     تاز
    0.38
    Activations Density 0.311%

    No Known Activations