© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15710
    Prev
    Next
    INDEX
    Explanations

    hard and compounds

    np_acts-logits-general · gemini-2.5-flash-lite

    intensity or difficulty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    एम
    0.60
    مک
    0.57
    на
    0.56
    트
    0.56
    ためには
    0.55
    ΟΥ
    0.55
    که
    0.54
    મિક
    0.54
    HTTPSampler
    0.53
    서
    0.53
    POSITIVE LOGITS
     hard
    1.20
     harder
    1.18
     HARD
    1.18
    硬
    1.18
     Hard
    1.16
    hard
    1.13
    Hard
    1.13
     hardest
    1.01
     hardness
    1.01
     duro
    0.99
    Activations Density 0.243%

    No Known Activations