© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132289
    Prev
    Next
    INDEX
    Explanations

    mentioning specific things

    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
    HOB
    0.42
    经典
    0.39
     ইপিআর
    0.38
    友
    0.38
     উড়
    0.38
     behold
    0.37
     tinker
    0.37
    Bro
    0.37
    ocompat
    0.36
    Finland
    0.36
    POSITIVE LOGITS
    }^{*}$
    0.41
     steals
    0.37
     newfound
    0.36
     だ
    0.35
    Scissors
    0.35
     Mostly
    0.35
     Każ
    0.35
     Теперь
    0.35
     Owned
    0.35
     Mỗi
    0.35
    Activations Density 0.000%

    No Known Activations