© 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. 109706
    Prev
    Next
    INDEX
    Explanations

    true love, halloween ops, Harry Potter

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

    American or variation of words

    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
     poems
    0.60
     woes
    0.57
     चाहर
    0.54
     괜
    0.52
     poema
    0.52
    poem
    0.52
    IH
    0.51
     poem
    0.50
     promoc
    0.50
     exposes
    0.50
    POSITIVE LOGITS
     امریکا
    0.48
    틱
    0.46
     امریک
    0.45
    غیر
    0.42
     Bases
    0.42
    貸
    0.42
     दुसरे
    0.41
    UnderTest
    0.41
    蔗
    0.40
    йти
    0.40
    Activations Density 0.000%

    No Known Activations