© 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. 156685
    Prev
    Next
    INDEX
    Explanations

    following links or buttons below

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

    instructions to choose one

    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
     like
    0.42
    rs
    0.42
    榭
    0.42
     mu
    0.41
    ='./
    0.40
     lihtsalt
    0.40
     möglicherweise
    0.39
     personer
    0.39
    差
    0.39
     Graeme
    0.39
    POSITIVE LOGITS
    ফ
    0.47
     ಕಲ
    0.46
     እንቅ
    0.45
    வண
    0.44
    寝
    0.43
    OpenCamera
    0.43
    遊び
    0.42
     এইচডি
    0.42
     ಕುಟುಂಬ
    0.42
    𒁕
    0.42
    Activations Density 0.000%

    No Known Activations