© 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. 248536
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ᱼ
    0.45
    on
    0.43
    ritional
    0.42
    adians
    0.42
    adium
    0.41
    icating
    0.41
     לך
    0.41
                             
    0.40
    rice
    0.40
     них
    0.40
    POSITIVE LOGITS
     mohabbat
    0.53
     Barangay
    0.51
    یثیت
    0.47
    衙
    0.44
     escritura
    0.44
     quatre
    0.43
     escalas
    0.43
     esfera
    0.42
    璎
    0.42
     heinous
    0.42
    Activations Density 0.005%

    No Known Activations