© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15465
    Prev
    Next
    INDEX
    Explanations

    specific examples and details

    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
     obiettivo
    0.50
     jedem
    0.49
    Для
    0.46
    න්ධ
    0.45
    たと
    0.43
    Pentru
    0.43
    untuk
    0.42
    }))$
    0.42
     inverso
    0.42
    為了
    0.42
    POSITIVE LOGITS
    IBR
    0.48
    j
    0.44
    ORI
    0.42
     exiting
    0.41
     outperforms
    0.40
     matchups
    0.40
     書き
    0.40
     leans
    0.38
    t
    0.38
    ic
    0.38
    Activations Density 0.001%

    No Known Activations