© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11344
    Prev
    Next
    INDEX
    Explanations

    geographical or metaphorical landscapes

    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_40_width_16k_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
    激动
    0.43
    捩
    0.40
     spir
    0.38
     scom
    0.37
     senz
    0.36
     Neto
    0.36
    गुण
    0.35
    блема
    0.35
    矢
    0.35
    漾
    0.35
    POSITIVE LOGITS
     landscape
    2.05
    landscape
    1.89
    Landscape
    1.83
     landscapes
    1.80
     Landscape
    1.78
     paysage
    1.59
     Landschaft
    1.51
     Landscapes
    1.49
     paisaje
    1.48
     landsc
    1.38
    Activations Density 0.086%

    No Known Activations