© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131110
    Prev
    Next
    INDEX
    Explanations

    finding what happens next

    np_acts-logits-general · gemini-2.5-flash-lite

    used for silicone powder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    शाली
    0.45
     savings
    0.45
    ®,
    0.43
     آدمی
    0.42
    医師
    0.41
     communiqué
    0.40
    гин
    0.40
     delusion
    0.40
     stalwart
    0.40
    ুধ
    0.39
    POSITIVE LOGITS
    𝘆
    0.57
     superficie
    0.57
    𝗡
    0.55
    𝗜
    0.54
     фаразлау
    0.53
    𝗘
    0.53
     szczeg
    0.51
     ư
    0.50
     ប៉ុ
    0.50
    𝘭
    0.49
    Activations Density 0.000%

    No Known Activations