© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138335
    Prev
    Next
    INDEX
    Explanations

    figure references

    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_16_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
    ﻤ
    1.26
    ﺒ
    1.15
    ﻠ
    1.12
    ﺭ
    1.09
    ﺤ
    1.09
    ﺮ
    1.08
    ﺎ
    1.05
    ﻄ
    0.98
    ﺸ
    0.97
    ll
    0.97
    POSITIVE LOGITS
    ти
    1.35
    er
    1.02
    тих
    0.92
    ad
    0.90
    ва
    0.90
    ко
    0.89
    ci
    0.88
    an
    0.87
    at
    0.85
    a
    0.84
    Activations Density 0.001%

    No Known Activations