© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98650
    Prev
    Next
    INDEX
    Explanations

    multiline blocks after |

    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
    ীবনী
    0.46
    𝖒
    0.44
    ቓ
    0.42
    粞
    0.42
    瞍
    0.41
    峮
    0.41
    拗
    0.40
    बीआई
    0.40
    aliśmy
    0.40
    佃
    0.40
    POSITIVE LOGITS
    central
    0.41
    clips
    0.38
    answers
    0.37
    SIL
    0.36
    quotes
    0.35
    initiated
    0.35
    diameter
    0.35
    Answers
    0.35
    +
    0.35
    homes
    0.34
    Activations Density 0.001%

    No Known Activations