© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 67
    Prev
    Next
    INDEX
    Explanations

    terraform random constructs

    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_65k_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
    Tas
    0.42
     Beratung
    0.40
    𝘰
    0.39
     Worked
    0.39
    Mie
    0.39
    ческое
    0.38
    Coe
    0.38
    tiket
    0.38
    édie
    0.38
     സാധ്യത
    0.38
    POSITIVE LOGITS
     orientation
    0.36
     allowed
    0.36
    allowed
    0.36
     orient
    0.35
     allows
    0.35
     विमा
    0.35
     Child
    0.34
     L
    0.34
     fence
    0.34
     constructs
    0.33
    Activations Density 0.030%

    No Known Activations