© 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. 114385
    Prev
    Next
    INDEX
    Explanations

    renewable energy and investments

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

    renewable energy

    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
    。
    0.59
    ۔
    0.58
    }$.
    0.57
    Α
    0.53
    ।
    0.52
     electrolytes
    0.52
    }$\
    0.51
     GHG
    0.50
    }$
    0.49
    umu
    0.49
    POSITIVE LOGITS
    هایی
    0.57
    isierten
    0.50
     সত্যিই
    0.48
     Jalis
    0.48
     هایی
    0.48
    isierte
    0.47
     Zeiten
    0.47
    ፊት
    0.47
    식을
    0.47
    ставить
    0.46
    Activations Density 0.025%

    No Known Activations