© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90807
    Prev
    Next
    INDEX
    Explanations

    exploring systems and information needs

    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
    θη
    0.50
    לו
    0.48
     উদ্বাস্তুদের
    0.45
    𝘄
    0.45
    roughly
    0.45
    始まる
    0.45
    𝘆
    0.44
     armoured
    0.44
    Ὑ
    0.44
     tyres
    0.43
    POSITIVE LOGITS
    v
    0.49
    u
    0.48
     geliş
    0.46
    á
    0.45
    l
    0.43
    es
    0.42
    al
    0.42
    ější
    0.42
     Due
    0.42
    akl
    0.42
    Activations Density 0.003%

    No Known Activations