© 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. 16-GEMMASCOPE-2-RES-262K
    7. 12997
    Prev
    Next
    INDEX
    Explanations

    preposition + noun/location/state

    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_16_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
     and
    0.51
     as
    0.46
     אבל
    0.45
     but
    0.44
     ಆದರೆ
    0.44
    ⟋
    0.44
     walled
    0.43
     with
    0.42
     বটে
    0.42
     scandals
    0.42
    POSITIVE LOGITS
    Ꭲ
    0.52
    Ν
    0.50
    Estamos
    0.48
    Installing
    0.47
    𝐇
    0.47
    К
    0.45
    Ρ
    0.45
    Dollars
    0.45
    eight
    0.45
    Ο
    0.45
    Activations Density 0.320%

    No Known Activations