© 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. 18354
    Prev
    Next
    INDEX
    Explanations

    descriptions of systems and states

    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
    7
    0.55
    Fc
    0.52
     eb
    0.51
     intento
    0.50
     undef
    0.49
     gob
    0.49
     explicit
    0.49
     금
    0.48
     invo
    0.48
     étale
    0.47
    POSITIVE LOGITS
    нього
    0.44
     ساتھ
    0.43
    ння
    0.43
     foundation
    0.42
     לפני
    0.42
    visions
    0.41
    Competitive
    0.41
    yssey
    0.40
    phasis
    0.40
    phalt
    0.40
    Activations Density 0.001%

    No Known Activations