© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11807
    Prev
    Next
    INDEX
    Explanations

    encoder and decoder architecture

    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
    ഈ
    0.43
     propagated
    0.42
     também
    0.42
     forsk
    0.41
    笉
    0.41
    ফেট
    0.41
     pfl
    0.41
    ")/
    0.40
    ましたが
    0.39
     juga
    0.39
    POSITIVE LOGITS
    Shel
    0.44
    Rew
    0.42
    remainder
    0.42
    Evalu
    0.42
    Unt
    0.41
    Evaluation
    0.40
    planet
    0.40
    Oriental
    0.40
    ponent
    0.40
    Creator
    0.40
    Activations Density 0.001%

    No Known Activations