© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200588
    Prev
    Next
    INDEX
    Explanations

    preposition followed by specific word

    np_acts-logits-general · gemini-2.5-flash-lite

    inherent meaning or ultimate purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colch
    0.43
     폭
    0.42
    ibilità
    0.41
    NEAR
    0.40
     առ
    0.40
    Kotlin
    0.40
     peł
    0.40
    TextArea
    0.40
     cuándo
    0.40
     nasıl
    0.40
    POSITIVE LOGITS
    fromUtf
    0.42
    టువంటి
    0.42
    利益
    0.41
     سوف
    0.40
     الذين
    0.39
     operatives
    0.39
    ∣
    0.39
     mnoho
    0.39
    )，
    0.38
    頤
    0.38
    Activations Density 0.001%

    No Known Activations