© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 124017
    Prev
    Next
    INDEX
    Explanations

    concepts relating to locations or actions

    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
    verson
    0.44
    !
    0.43
    ół
    0.42
    PT
    0.42
    ansion
    0.41
    Kelly
    0.41
     Kelly
    0.41
     telefoon
    0.41
     많
    0.40
     Too
    0.40
    POSITIVE LOGITS
    چھا
    0.42
    ழ்ச்ச
    0.42
     cutaneous
    0.41
    埜
    0.41
     Amazonas
    0.41
    தி
    0.40
     objetivo
    0.40
     LANA
    0.40
    শোধ
    0.39
     Beziehungen
    0.39
    Activations Density 0.007%

    No Known Activations