© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 4481
    Prev
    Next
    INDEX
    Explanations

    can be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     shall
    0.48
    .
    0.48
     would
    0.47
     couldn
    0.47
     MUST
    0.46
     should
    0.46
     must
    0.46
    shall
    0.46
    cannot
    0.45
    ?
    0.44
    POSITIVE LOGITS
    甚至
    0.44
    甚至是
    0.43
     आल्सो
    0.41
    いろいろ
    0.41
     myös
    0.41
     اوقات
    0.41
     pathologies
    0.40
    든
    0.40
     stigmat
    0.39
     ankaŭ
    0.39
    Activations Density 0.055%

    No Known Activations