© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 38497
    Prev
    Next
    INDEX
    Explanations

    reasonably well

    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
    钮
    0.47
     busiest
    0.46
     buffs
    0.45
     limbs
    0.43
    ffected
    0.43
     instructs
    0.42
    u
    0.42
    ە
    0.41
    每一個
    0.41
     బొ
    0.41
    POSITIVE LOGITS
    setFillColor
    0.46
     conferma
    0.46
     raccont
    0.44
    നട
    0.42
     cạnh
    0.42
     Syn
    0.41
    Invoice
    0.41
    HOLD
    0.41
    sony
    0.41
     đúng
    0.40
    Activations Density 0.001%

    No Known Activations