© 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. 112164
    Prev
    Next
    INDEX
    Explanations

    specific steps or explanations

    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
    ок
    0.45
     displacement
    0.44
    コ
    0.42
    displacement
    0.42
    עה
    0.40
    ブ
    0.40
    ﯽ
    0.40
    اک
    0.39
     Trails
    0.39
    <0x82>
    0.39
    POSITIVE LOGITS
     pursuant
    0.55
     Pursuant
    0.46
    Acetoxy
    0.43
    Lloyd
    0.41
     Eingang
    0.41
    ngthen
    0.39
    HandleFunc
    0.39
    になり
    0.38
     умови
    0.38
    achery
    0.38
    Activations Density 0.009%

    No Known Activations