© 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. 195542
    Prev
    Next
    INDEX
    Explanations

    factual history, dreams, !

    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
     ประมาณ
    0.39
    োয়
    0.37
     mev
    0.36
     голосо
    0.36
     geology
    0.36
     &_
    0.36
     সিদ্ধান্ত
    0.36
    凃
    0.35
     灬
    0.35
    }&=
    0.35
    POSITIVE LOGITS
    coe
    0.45
    最低
    0.39
    以外
    0.39
     señalar
    0.39
    탱
    0.38
    aldi
    0.37
    $/
    0.37
     détach
    0.37
    라우
    0.37
    pr
    0.36
    Activations Density 0.000%

    No Known Activations