© 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. 38874
    Prev
    Next
    INDEX
    Explanations

    different ways of relating

    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
     DJs
    0.48
     excludes
    0.48
    }%
    0.46
    \%$
    0.45
     Optionally
    0.45
     ラ
    0.44
     ジャ
    0.44
     $+
    0.44
    |$
    0.44
     cameos
    0.44
    POSITIVE LOGITS
     اینکه
    0.45
    因为
    0.43
    它們
    0.42
     laborator
    0.40
     neutron
    0.40
    原始
    0.39
    ikuti
    0.39
    because
    0.38
    Because
    0.38
    它们
    0.38
    Activations Density 0.009%

    No Known Activations