© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7804
    Prev
    Next
    INDEX
    Explanations

    including protecting

    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_65k_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
     কিংবা
    0.66
     oppure
    0.63
     অথবা
    0.60
     hingegen
    0.51
    ેશન
    0.47
    c
    0.45
    s
    0.44
     is
    0.44
    ized
    0.43
    od
    0.43
    POSITIVE LOGITS
    INCLUDING
    0.61
    但不
    0.59
     stints
    0.57
    BOTH
    0.55
     بسیاری
    0.53
    including
    0.52
    𝚅
    0.51
    म्ह
    0.50
    人も
    0.49
    Including
    0.48
    Activations Density 0.075%

    No Known Activations