© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43299
    Prev
    Next
    INDEX
    Explanations

    body starts, tokenizer

    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_31_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
    אה
    0.51
    נ
    0.50
     manuf
    0.49
    נס
    0.49
     humains
    0.49
     marketers
    0.48
     причиной
    0.48
     overcrow
    0.46
     listeners
    0.46
    }+...
    0.46
    POSITIVE LOGITS
    ivatives
    0.48
    Array
    0.45
    vá
    0.45
    SIBILITY
    0.44
    (
    0.43
    etri
    0.42
    isection
    0.41
    ENGTH
    0.41
    öpf
    0.40
    of
    0.40
    Activations Density 0.001%

    No Known Activations