© 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. 70695
    Prev
    Next
    INDEX
    Explanations

    density altitude

    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
    મેન્ટ
    0.51
    이다
    0.50
     ступен
    0.50
     оптима
    0.49
     εν
    0.48
    한다
    0.47
    酺
    0.47
     автофо
    0.47
     את
    0.46
     mentorship
    0.46
    POSITIVE LOGITS
    j
    0.54
    n
    0.52
    f
    0.48
    jing
    0.47
     unwittingly
    0.46
    very
    0.45
     unknowingly
    0.45
     enorme
    0.45
    í
    0.43
    ee
    0.43
    Activations Density 0.003%

    No Known Activations