© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133820
    Prev
    Next
    INDEX
    Explanations

    simple example

    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_40_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
     paths
    0.40
    拡張
    0.40
    ⑬
    0.37
    Who
    0.37
    ژگی
    0.37
     मूवमेंट
    0.37
    amiliar
    0.36
    ocentric
    0.36
     Paths
    0.36
    ぺ
    0.36
    POSITIVE LOGITS
     Waq
    0.43
    ക്ര
    0.42
    ؑ
    0.41
    ပိုင်း
    0.40
    सैन
    0.40
    আপ
    0.39
     Greene
    0.38
     Craig
    0.38
     custos
    0.37
    aikum
    0.37
    Activations Density 0.000%

    No Known Activations