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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 32378
    Prev
    Next
    INDEX
    Explanations

    instruction to act

    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
    ).}
    0.65
    ).
    0.64
    becomes
    0.63
    .)
    0.63
    ):
    0.62
    )
    0.61
    =
    0.60
    }
    0.59
    )=
    0.58
    ’.
    0.58
    POSITIVE LOGITS
     نیچے
    0.61
    RequestListener
    0.57
     алыңыз
    0.55
    PopupButton
    0.54
     basilaires
    0.54
    Выберите
    0.54
    ವೇಂದ್ರ
    0.53
     지하
    0.53
    덱
    0.53
     εισ
    0.53
    Activations Density 0.018%

    No Known Activations